{
 "note": "集計。rate は割合（0〜1）、counts は件数。2 回測った値は runs の順（1 回目・2 回目）。scopes.all は全部の問い、scopes.excluded は問いを除外した後。",
 "meta": {
  "results_dir": "scripts/hallucination_benchmark/results_main",
  "labels_dir": "scripts/hallucination_benchmark/out_main",
  "n_models": 16,
  "n_questions_all": 168,
  "n_excluded": 39,
  "judge_used": true,
  "judge_rows": 13200,
  "fig_scope": "excluded",
  "runs": 2,
  "n_outputs": 51072,
  "n_questions_kept": 129,
  "kept_kinds": {
   "number": 101,
   "name": 23,
   "date": 5
  },
  "kept_origins": {
   "own_set": 75,
   "new": 54
  }
 },
 "terms": {
  "ctx": {
   "answerable": "答えのある文書",
   "near": "答えの無い文書（近い話題）",
   "far": "答えの無い文書（別の話題）",
   "nodoc": "文書なし"
  },
  "prompt": {
   "plain": "指示なし",
   "abstain": "辞退の指示あり",
   "quote": "根拠の引用",
   "nodoc": "文書なし"
  },
  "final_answerable": {
   "correct": "正答",
   "other": "誤答",
   "abstain": "不要な辞退",
   "hedged": "断りながら答えた",
   "unresolved": "答えも辞退も無い"
  },
  "final_unanswerable": {
   "abstain": "正しい辞退",
   "other": "答えを出した",
   "hedged": "断りながら答えた",
   "correct": "正解と一致",
   "unresolved": "答えも辞退も無い"
  },
  "answered": "答えを出した割合＝（答えを出した＋断りながら答えた）÷ 問いの数"
 },
 "definitions": {
  "range": "モデルをまたいだ範囲: lo は全モデル・2 回のうち最も小さい値、hi は最も大きい値（lo_model・hi_model はその値を出したモデル）。mean_lo・mean_hi は各モデルの 2 回の平均の最小・最大、median_of_means はその中央値。",
  "tradeoff": "drop = 近い話題で答えを出した割合（指示なし）− 同（辞退の指示あり）、rise = 答えのある文書での不要な辞退（辞退の指示あり）− 同（指示なし）。単位はポイント。回ごとに計算し、2 回を小さい方〜大きい方で書く。",
  "test": "同じ問いどうしの対の正確な符号検定（両側）。指示なし 対 辞退の指示あり。回ごとに別々に検定し、モデルの数で Holm の補正。significant_both = 2 回とも Holm 補正後の p が 0.05 未満。"
 },
 "order": [
  "qwen3:8b",
  "qwen3:14b",
  "qwen3:30b",
  "qwen3.5:9b",
  "qwen3.5:27b",
  "gemma3:12b",
  "gemma3:27b",
  "gemma4:12b",
  "gemma4:26b",
  "gpt-oss:20b",
  "gpt-oss:120b",
  "deepseek-r1:8b",
  "deepseek-r1:14b",
  "llama3.1:8b",
  "mistral-small3.2:24b",
  "phi4:14b"
 ],
 "scopes": {
  "all": {
   "n_questions": 168,
   "cells": {
    "qwen3:8b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         157,
         156
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         11,
         12
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         11,
         12
        ]
       },
       "rates": {
        "correct": [
         0.9345238095238095,
         0.9285714285714286
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.06547619047619048,
         0.07142857142857142
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.06547619047619048,
         0.07142857142857142
        ]
       },
       "disp": {
        "correct": {
         "p0": "93",
         "p1": "92.9〜93.5",
         "count": "156〜157"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "7",
         "p1": "6.5〜7.1",
         "count": "11〜12"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "7",
         "p1": "6.5〜7.1",
         "count": "11〜12"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         6,
         6
        ],
        "abstain": [
         22,
         25
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         140,
         137
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         140,
         137
        ]
       },
       "rates": {
        "correct": [
         0.03571428571428571,
         0.03571428571428571
        ],
        "abstain": [
         0.13095238095238096,
         0.1488095238095238
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.8333333333333334,
         0.8154761904761905
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.8333333333333334,
         0.8154761904761905
        ]
       },
       "disp": {
        "correct": {
         "p0": "4",
         "p1": "3.6",
         "count": "6"
        },
        "abstain": {
         "p0": "13〜15",
         "p1": "13.1〜14.9",
         "count": "22〜25"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "82〜83",
         "p1": "81.5〜83.3",
         "count": "137〜140"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "82〜83",
         "p1": "81.5〜83.3",
         "count": "137〜140"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         1,
         0
        ],
        "abstain": [
         91,
         88
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         76,
         80
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         76,
         80
        ]
       },
       "rates": {
        "correct": [
         0.005952380952380952,
         0.0
        ],
        "abstain": [
         0.5416666666666666,
         0.5238095238095238
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.4523809523809524,
         0.47619047619047616
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.4523809523809524,
         0.47619047619047616
        ]
       },
       "disp": {
        "correct": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        },
        "abstain": {
         "p0": "52〜54",
         "p1": "52.4〜54.2",
         "count": "88〜91"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "45〜48",
         "p1": "45.2〜47.6",
         "count": "76〜80"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "45〜48",
         "p1": "45.2〜47.6",
         "count": "76〜80"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         153,
         153
        ],
        "abstain": [
         4,
         4
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         11,
         11
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         11,
         11
        ]
       },
       "rates": {
        "correct": [
         0.9107142857142857,
         0.9107142857142857
        ],
        "abstain": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.06547619047619048,
         0.06547619047619048
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.06547619047619048,
         0.06547619047619048
        ]
       },
       "disp": {
        "correct": {
         "p0": "91",
         "p1": "91.1",
         "count": "153"
        },
        "abstain": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "7",
         "p1": "6.5",
         "count": "11"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "7",
         "p1": "6.5",
         "count": "11"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         3,
         3
        ],
        "abstain": [
         133,
         133
        ],
        "hedged": [
         1,
         1
        ],
        "other": [
         31,
         31
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         32,
         32
        ]
       },
       "rates": {
        "correct": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "abstain": [
         0.7916666666666666,
         0.7916666666666666
        ],
        "hedged": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "other": [
         0.18452380952380953,
         0.18452380952380953
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.19047619047619047,
         0.19047619047619047
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "abstain": {
         "p0": "79",
         "p1": "79.2",
         "count": "133"
        },
        "hedged": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "other": {
         "p0": "18",
         "p1": "18.5",
         "count": "31"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "19",
         "p1": "19.0",
         "count": "32"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         167,
         167
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9940476190476191,
         0.9940476190476191
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "99.4",
         "count": "167"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         153,
         157
        ],
        "abstain": [
         6,
         6
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         9,
         5
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         9,
         5
        ]
       },
       "rates": {
        "correct": [
         0.9107142857142857,
         0.9345238095238095
        ],
        "abstain": [
         0.03571428571428571,
         0.03571428571428571
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.05357142857142857,
         0.02976190476190476
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.05357142857142857,
         0.02976190476190476
        ]
       },
       "disp": {
        "correct": {
         "p0": "91〜93",
         "p1": "91.1〜93.5",
         "count": "153〜157"
        },
        "abstain": {
         "p0": "4",
         "p1": "3.6",
         "count": "6"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3〜5",
         "p1": "3.0〜5.4",
         "count": "5〜9"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3〜5",
         "p1": "3.0〜5.4",
         "count": "5〜9"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         4,
         4
        ],
        "abstain": [
         140,
         139
        ],
        "hedged": [
         0,
         1
        ],
        "other": [
         23,
         23
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         23,
         24
        ]
       },
       "rates": {
        "correct": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "abstain": [
         0.8333333333333334,
         0.8273809523809523
        ],
        "hedged": [
         0.0,
         0.005952380952380952
        ],
        "other": [
         0.13690476190476192,
         0.13690476190476192
        ],
        "unresolved": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "answered": [
         0.13690476190476192,
         0.14285714285714285
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "abstain": {
         "p0": "83",
         "p1": "82.7〜83.3",
         "count": "139〜140"
        },
        "hedged": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        },
        "other": {
         "p0": "14",
         "p1": "13.7",
         "count": "23"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "answered": {
         "p0": "14",
         "p1": "13.7〜14.3",
         "count": "23〜24"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "qwen3:14b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         164,
         163
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         5
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         5
        ]
       },
       "rates": {
        "correct": [
         0.9761904761904762,
         0.9702380952380952
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023809523809523808,
         0.02976190476190476
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023809523809523808,
         0.02976190476190476
        ]
       },
       "disp": {
        "correct": {
         "p0": "97〜98",
         "p1": "97.0〜97.6",
         "count": "163〜164"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2〜3",
         "p1": "2.4〜3.0",
         "count": "4〜5"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2〜3",
         "p1": "2.4〜3.0",
         "count": "4〜5"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         4,
         4
        ],
        "abstain": [
         48,
         43
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         116,
         121
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         116,
         121
        ]
       },
       "rates": {
        "correct": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "abstain": [
         0.2857142857142857,
         0.25595238095238093
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.6904761904761905,
         0.7202380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.6904761904761905,
         0.7202380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "abstain": {
         "p0": "26〜29",
         "p1": "25.6〜28.6",
         "count": "43〜48"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "69〜72",
         "p1": "69.0〜72.0",
         "count": "116〜121"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "69〜72",
         "p1": "69.0〜72.0",
         "count": "116〜121"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         128,
         128
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         40,
         40
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         40,
         40
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.7619047619047619,
         0.7619047619047619
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.23809523809523808,
         0.23809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.23809523809523808,
         0.23809523809523808
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "76",
         "p1": "76.2",
         "count": "128"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "24",
         "p1": "23.8",
         "count": "40"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "24",
         "p1": "23.8",
         "count": "40"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         163,
         162
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9702380952380952,
         0.9642857142857143
        ],
        "abstain": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.017857142857142856,
         0.023809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.017857142857142856,
         0.023809523809523808
        ]
       },
       "disp": {
        "correct": {
         "p0": "96〜97",
         "p1": "96.4〜97.0",
         "count": "162〜163"
        },
        "abstain": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         3,
         3
        ],
        "abstain": [
         137,
         137
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         28,
         28
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         28,
         28
        ]
       },
       "rates": {
        "correct": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "abstain": [
         0.8154761904761905,
         0.8154761904761905
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.16666666666666666,
         0.16666666666666666
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.16666666666666666,
         0.16666666666666666
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "abstain": {
         "p0": "82",
         "p1": "81.5",
         "count": "137"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "17",
         "p1": "16.7",
         "count": "28"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "17",
         "p1": "16.7",
         "count": "28"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         160,
         159
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         6,
         7
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         6,
         7
        ]
       },
       "rates": {
        "correct": [
         0.9523809523809523,
         0.9464285714285714
        ],
        "abstain": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.03571428571428571,
         0.041666666666666664
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.03571428571428571,
         0.041666666666666664
        ]
       },
       "disp": {
        "correct": {
         "p0": "95",
         "p1": "94.6〜95.2",
         "count": "159〜160"
        },
        "abstain": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4",
         "p1": "3.6〜4.2",
         "count": "6〜7"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "4",
         "p1": "3.6〜4.2",
         "count": "6〜7"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         2,
         2
        ],
        "abstain": [
         117,
         118
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         49,
         48
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         49,
         48
        ]
       },
       "rates": {
        "correct": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "abstain": [
         0.6964285714285714,
         0.7023809523809523
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.2916666666666667,
         0.2857142857142857
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.2916666666666667,
         0.2857142857142857
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "abstain": {
         "p0": "70",
         "p1": "69.6〜70.2",
         "count": "117〜118"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "29",
         "p1": "28.6〜29.2",
         "count": "48〜49"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "29",
         "p1": "28.6〜29.2",
         "count": "48〜49"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         167,
         167
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9940476190476191,
         0.9940476190476191
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "99.4",
         "count": "167"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      }
     }
    },
    "qwen3:30b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         155,
         156
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         11,
         10
        ],
        "unresolved": [
         2,
         2
        ],
        "answered": [
         11,
         10
        ]
       },
       "rates": {
        "correct": [
         0.9226190476190477,
         0.9285714285714286
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.06547619047619048,
         0.05952380952380952
        ],
        "unresolved": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "answered": [
         0.06547619047619048,
         0.05952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "92〜93",
         "p1": "92.3〜92.9",
         "count": "155〜156"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "6〜7",
         "p1": "6.0〜6.5",
         "count": "10〜11"
        },
        "unresolved": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "answered": {
         "p0": "6〜7",
         "p1": "6.0〜6.5",
         "count": "10〜11"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         8,
         9
        ],
        "abstain": [
         23,
         20
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         107,
         101
        ],
        "unresolved": [
         30,
         38
        ],
        "answered": [
         107,
         101
        ]
       },
       "rates": {
        "correct": [
         0.047619047619047616,
         0.05357142857142857
        ],
        "abstain": [
         0.13690476190476192,
         0.11904761904761904
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.6369047619047619,
         0.6011904761904762
        ],
        "unresolved": [
         0.17857142857142858,
         0.2261904761904762
        ],
        "answered": [
         0.6369047619047619,
         0.6011904761904762
        ]
       },
       "disp": {
        "correct": {
         "p0": "5",
         "p1": "4.8〜5.4",
         "count": "8〜9"
        },
        "abstain": {
         "p0": "12〜14",
         "p1": "11.9〜13.7",
         "count": "20〜23"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "60〜64",
         "p1": "60.1〜63.7",
         "count": "101〜107"
        },
        "unresolved": {
         "p0": "18〜23",
         "p1": "17.9〜22.6",
         "count": "30〜38"
        },
        "answered": {
         "p0": "60〜64",
         "p1": "60.1〜63.7",
         "count": "101〜107"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         106,
         105
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         54,
         54
        ],
        "unresolved": [
         7,
         8
        ],
        "answered": [
         54,
         54
        ]
       },
       "rates": {
        "correct": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "abstain": [
         0.6309523809523809,
         0.625
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.32142857142857145,
         0.32142857142857145
        ],
        "unresolved": [
         0.041666666666666664,
         0.047619047619047616
        ],
        "answered": [
         0.32142857142857145,
         0.32142857142857145
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "abstain": {
         "p0": "63",
         "p1": "62.5〜63.1",
         "count": "105〜106"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "32",
         "p1": "32.1",
         "count": "54"
        },
        "unresolved": {
         "p0": "4〜5",
         "p1": "4.2〜4.8",
         "count": "7〜8"
        },
        "answered": {
         "p0": "32",
         "p1": "32.1",
         "count": "54"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         159,
         156
        ],
        "abstain": [
         2,
         1
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         7,
         10
        ],
        "unresolved": [
         0,
         1
        ],
        "answered": [
         7,
         10
        ]
       },
       "rates": {
        "correct": [
         0.9464285714285714,
         0.9285714285714286
        ],
        "abstain": [
         0.011904761904761904,
         0.005952380952380952
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.041666666666666664,
         0.05952380952380952
        ],
        "unresolved": [
         0.0,
         0.005952380952380952
        ],
        "answered": [
         0.041666666666666664,
         0.05952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "93〜95",
         "p1": "92.9〜94.6",
         "count": "156〜159"
        },
        "abstain": {
         "p0": "1",
         "p1": "0.6〜1.2",
         "count": "1〜2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4〜6",
         "p1": "4.2〜6.0",
         "count": "7〜10"
        },
        "unresolved": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        },
        "answered": {
         "p0": "4〜6",
         "p1": "4.2〜6.0",
         "count": "7〜10"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         6,
         7
        ],
        "abstain": [
         122,
         123
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         35,
         36
        ],
        "unresolved": [
         5,
         2
        ],
        "answered": [
         35,
         36
        ]
       },
       "rates": {
        "correct": [
         0.03571428571428571,
         0.041666666666666664
        ],
        "abstain": [
         0.7261904761904762,
         0.7321428571428571
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.20833333333333334,
         0.21428571428571427
        ],
        "unresolved": [
         0.02976190476190476,
         0.011904761904761904
        ],
        "answered": [
         0.20833333333333334,
         0.21428571428571427
        ]
       },
       "disp": {
        "correct": {
         "p0": "4",
         "p1": "3.6〜4.2",
         "count": "6〜7"
        },
        "abstain": {
         "p0": "73",
         "p1": "72.6〜73.2",
         "count": "122〜123"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "21",
         "p1": "20.8〜21.4",
         "count": "35〜36"
        },
        "unresolved": {
         "p0": "1〜3",
         "p1": "1.2〜3.0",
         "count": "2〜5"
        },
        "answered": {
         "p0": "21",
         "p1": "20.8〜21.4",
         "count": "35〜36"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         167,
         167
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9940476190476191,
         0.9940476190476191
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "99.4",
         "count": "167"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         163,
         162
        ],
        "abstain": [
         1,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9702380952380952,
         0.9642857142857143
        ],
        "abstain": [
         0.005952380952380952,
         0.011904761904761904
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023809523809523808,
         0.023809523809523808
        ]
       },
       "disp": {
        "correct": {
         "p0": "96〜97",
         "p1": "96.4〜97.0",
         "count": "162〜163"
        },
        "abstain": {
         "p0": "1",
         "p1": "0.6〜1.2",
         "count": "1〜2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         5,
         7
        ],
        "abstain": [
         124,
         121
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         32,
         30
        ],
        "unresolved": [
         7,
         10
        ],
        "answered": [
         32,
         30
        ]
       },
       "rates": {
        "correct": [
         0.02976190476190476,
         0.041666666666666664
        ],
        "abstain": [
         0.7380952380952381,
         0.7202380952380952
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.19047619047619047,
         0.17857142857142858
        ],
        "unresolved": [
         0.041666666666666664,
         0.05952380952380952
        ],
        "answered": [
         0.19047619047619047,
         0.17857142857142858
        ]
       },
       "disp": {
        "correct": {
         "p0": "3〜4",
         "p1": "3.0〜4.2",
         "count": "5〜7"
        },
        "abstain": {
         "p0": "72〜74",
         "p1": "72.0〜73.8",
         "count": "121〜124"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "18〜19",
         "p1": "17.9〜19.0",
         "count": "30〜32"
        },
        "unresolved": {
         "p0": "4〜6",
         "p1": "4.2〜6.0",
         "count": "7〜10"
        },
        "answered": {
         "p0": "18〜19",
         "p1": "17.9〜19.0",
         "count": "30〜32"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         166,
         166
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9880952380952381,
         0.9880952380952381
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "98.8",
         "count": "166"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      }
     }
    },
    "qwen3.5:9b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         162,
         163
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         3
        ]
       },
       "rates": {
        "correct": [
         0.9642857142857143,
         0.9702380952380952
        ],
        "abstain": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023809523809523808,
         0.017857142857142856
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023809523809523808,
         0.017857142857142856
        ]
       },
       "disp": {
        "correct": {
         "p0": "96〜97",
         "p1": "96.4〜97.0",
         "count": "162〜163"
        },
        "abstain": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         5,
         5
        ],
        "abstain": [
         97,
         96
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         66,
         67
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         66,
         67
        ]
       },
       "rates": {
        "correct": [
         0.02976190476190476,
         0.02976190476190476
        ],
        "abstain": [
         0.5773809523809523,
         0.5714285714285714
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.39285714285714285,
         0.39880952380952384
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.39285714285714285,
         0.39880952380952384
        ]
       },
       "disp": {
        "correct": {
         "p0": "3",
         "p1": "3.0",
         "count": "5"
        },
        "abstain": {
         "p0": "57〜58",
         "p1": "57.1〜57.7",
         "count": "96〜97"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "39〜40",
         "p1": "39.3〜39.9",
         "count": "66〜67"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "39〜40",
         "p1": "39.3〜39.9",
         "count": "66〜67"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         159,
         160
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         9,
         8
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         9,
         8
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9464285714285714,
         0.9523809523809523
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.05357142857142857,
         0.047619047619047616
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.05357142857142857,
         0.047619047619047616
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "95",
         "p1": "94.6〜95.2",
         "count": "159〜160"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5",
         "p1": "4.8〜5.4",
         "count": "8〜9"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "5",
         "p1": "4.8〜5.4",
         "count": "8〜9"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         159,
         159
        ],
        "abstain": [
         8,
         8
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.9464285714285714,
         0.9464285714285714
        ],
        "abstain": [
         0.047619047619047616,
         0.047619047619047616
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "95",
         "p1": "94.6",
         "count": "159"
        },
        "abstain": {
         "p0": "5",
         "p1": "4.8",
         "count": "8"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         3,
         3
        ],
        "abstain": [
         146,
         147
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         19,
         18
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         19,
         18
        ]
       },
       "rates": {
        "correct": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "abstain": [
         0.8690476190476191,
         0.875
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.1130952380952381,
         0.10714285714285714
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.1130952380952381,
         0.10714285714285714
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "abstain": {
         "p0": "87〜88",
         "p1": "86.9〜87.5",
         "count": "146〜147"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "11",
         "p1": "10.7〜11.3",
         "count": "18〜19"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "11",
         "p1": "10.7〜11.3",
         "count": "18〜19"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         107,
         107
        ],
        "abstain": [
         58,
         58
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         3
        ]
       },
       "rates": {
        "correct": [
         0.6369047619047619,
         0.6369047619047619
        ],
        "abstain": [
         0.34523809523809523,
         0.34523809523809523
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.017857142857142856,
         0.017857142857142856
        ]
       },
       "disp": {
        "correct": {
         "p0": "64",
         "p1": "63.7",
         "count": "107"
        },
        "abstain": {
         "p0": "35",
         "p1": "34.5",
         "count": "58"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         160,
         160
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         7,
         7
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         7,
         7
        ]
       },
       "rates": {
        "correct": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "abstain": [
         0.9523809523809523,
         0.9523809523809523
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.041666666666666664,
         0.041666666666666664
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.041666666666666664,
         0.041666666666666664
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "abstain": {
         "p0": "95",
         "p1": "95.2",
         "count": "160"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4",
         "p1": "4.2",
         "count": "7"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "4",
         "p1": "4.2",
         "count": "7"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "qwen3.5:27b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         167,
         167
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.9940476190476191,
         0.9940476190476191
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "99",
         "p1": "99.4",
         "count": "167"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         3,
         3
        ],
        "abstain": [
         125,
         125
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         40,
         40
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         40,
         40
        ]
       },
       "rates": {
        "correct": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "abstain": [
         0.7440476190476191,
         0.7440476190476191
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.23809523809523808,
         0.23809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.23809523809523808,
         0.23809523809523808
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "abstain": {
         "p0": "74",
         "p1": "74.4",
         "count": "125"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "24",
         "p1": "23.8",
         "count": "40"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "24",
         "p1": "23.8",
         "count": "40"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         167,
         166
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         2
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         2
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9940476190476191,
         0.9880952380952381
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.011904761904761904
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.005952380952380952,
         0.011904761904761904
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "98.8〜99.4",
         "count": "166〜167"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6〜1.2",
         "count": "1〜2"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6〜1.2",
         "count": "1〜2"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         164,
         163
        ],
        "abstain": [
         3,
         4
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.9761904761904762,
         0.9702380952380952
        ],
        "abstain": [
         0.017857142857142856,
         0.023809523809523808
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "97〜98",
         "p1": "97.0〜97.6",
         "count": "163〜164"
        },
        "abstain": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         2,
         2
        ],
        "abstain": [
         159,
         159
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         7,
         7
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         7,
         7
        ]
       },
       "rates": {
        "correct": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "abstain": [
         0.9464285714285714,
         0.9464285714285714
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.041666666666666664,
         0.041666666666666664
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.041666666666666664,
         0.041666666666666664
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "abstain": {
         "p0": "95",
         "p1": "94.6",
         "count": "159"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4",
         "p1": "4.2",
         "count": "7"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "4",
         "p1": "4.2",
         "count": "7"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         166,
         166
        ],
        "abstain": [
         1,
         1
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.9880952380952381,
         0.9880952380952381
        ],
        "abstain": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "99",
         "p1": "98.8",
         "count": "166"
        },
        "abstain": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         5,
         5
        ],
        "abstain": [
         154,
         153
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         9,
         10
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         9,
         10
        ]
       },
       "rates": {
        "correct": [
         0.02976190476190476,
         0.02976190476190476
        ],
        "abstain": [
         0.9166666666666666,
         0.9107142857142857
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.05357142857142857,
         0.05952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.05357142857142857,
         0.05952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "3",
         "p1": "3.0",
         "count": "5"
        },
        "abstain": {
         "p0": "91〜92",
         "p1": "91.1〜91.7",
         "count": "153〜154"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5〜6",
         "p1": "5.4〜6.0",
         "count": "9〜10"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "5〜6",
         "p1": "5.4〜6.0",
         "count": "9〜10"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "gemma3:12b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         161,
         161
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         7,
         7
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         7,
         7
        ]
       },
       "rates": {
        "correct": [
         0.9583333333333334,
         0.9583333333333334
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.041666666666666664,
         0.041666666666666664
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.041666666666666664,
         0.041666666666666664
        ]
       },
       "disp": {
        "correct": {
         "p0": "96",
         "p1": "95.8",
         "count": "161"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4",
         "p1": "4.2",
         "count": "7"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "4",
         "p1": "4.2",
         "count": "7"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         2,
         2
        ],
        "abstain": [
         96,
         97
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         69,
         67
        ],
        "unresolved": [
         1,
         2
        ],
        "answered": [
         69,
         67
        ]
       },
       "rates": {
        "correct": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "abstain": [
         0.5714285714285714,
         0.5773809523809523
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.4107142857142857,
         0.39880952380952384
        ],
        "unresolved": [
         0.005952380952380952,
         0.011904761904761904
        ],
        "answered": [
         0.4107142857142857,
         0.39880952380952384
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "abstain": {
         "p0": "57〜58",
         "p1": "57.1〜57.7",
         "count": "96〜97"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "40〜41",
         "p1": "39.9〜41.1",
         "count": "67〜69"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.6〜1.2",
         "count": "1〜2"
        },
        "answered": {
         "p0": "40〜41",
         "p1": "39.9〜41.1",
         "count": "67〜69"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         161,
         162
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         7,
         6
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         7,
         6
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9583333333333334,
         0.9642857142857143
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.041666666666666664,
         0.03571428571428571
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.041666666666666664,
         0.03571428571428571
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "96",
         "p1": "95.8〜96.4",
         "count": "161〜162"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4",
         "p1": "3.6〜4.2",
         "count": "6〜7"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "4",
         "p1": "3.6〜4.2",
         "count": "6〜7"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         157,
         158
        ],
        "abstain": [
         4,
         4
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         7,
         6
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         7,
         6
        ]
       },
       "rates": {
        "correct": [
         0.9345238095238095,
         0.9404761904761905
        ],
        "abstain": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.041666666666666664,
         0.03571428571428571
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.041666666666666664,
         0.03571428571428571
        ]
       },
       "disp": {
        "correct": {
         "p0": "93〜94",
         "p1": "93.5〜94.0",
         "count": "157〜158"
        },
        "abstain": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4",
         "p1": "3.6〜4.2",
         "count": "6〜7"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "4",
         "p1": "3.6〜4.2",
         "count": "6〜7"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         2,
         2
        ],
        "abstain": [
         137,
         136
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         29,
         30
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         29,
         30
        ]
       },
       "rates": {
        "correct": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "abstain": [
         0.8154761904761905,
         0.8095238095238095
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.17261904761904762,
         0.17857142857142858
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.17261904761904762,
         0.17857142857142858
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "abstain": {
         "p0": "81〜82",
         "p1": "81.0〜81.5",
         "count": "136〜137"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "17〜18",
         "p1": "17.3〜17.9",
         "count": "29〜30"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "17〜18",
         "p1": "17.3〜17.9",
         "count": "29〜30"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         162,
         161
        ],
        "abstain": [
         5,
         6
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.9642857142857143,
         0.9583333333333334
        ],
        "abstain": [
         0.02976190476190476,
         0.03571428571428571
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "96",
         "p1": "95.8〜96.4",
         "count": "161〜162"
        },
        "abstain": {
         "p0": "3〜4",
         "p1": "3.0〜3.6",
         "count": "5〜6"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         144,
         144
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         23,
         23
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         23,
         23
        ]
       },
       "rates": {
        "correct": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "abstain": [
         0.8571428571428571,
         0.8571428571428571
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.13690476190476192,
         0.13690476190476192
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.13690476190476192,
         0.13690476190476192
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "abstain": {
         "p0": "86",
         "p1": "85.7",
         "count": "144"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "14",
         "p1": "13.7",
         "count": "23"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "14",
         "p1": "13.7",
         "count": "23"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "gemma3:27b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         161,
         161
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         7,
         7
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         7,
         7
        ]
       },
       "rates": {
        "correct": [
         0.9583333333333334,
         0.9583333333333334
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.041666666666666664,
         0.041666666666666664
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.041666666666666664,
         0.041666666666666664
        ]
       },
       "disp": {
        "correct": {
         "p0": "96",
         "p1": "95.8",
         "count": "161"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4",
         "p1": "4.2",
         "count": "7"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "4",
         "p1": "4.2",
         "count": "7"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         8,
         8
        ],
        "abstain": [
         74,
         76
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         83,
         81
        ],
        "unresolved": [
         3,
         3
        ],
        "answered": [
         83,
         81
        ]
       },
       "rates": {
        "correct": [
         0.047619047619047616,
         0.047619047619047616
        ],
        "abstain": [
         0.44047619047619047,
         0.4523809523809524
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.49404761904761907,
         0.48214285714285715
        ],
        "unresolved": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "answered": [
         0.49404761904761907,
         0.48214285714285715
        ]
       },
       "disp": {
        "correct": {
         "p0": "5",
         "p1": "4.8",
         "count": "8"
        },
        "abstain": {
         "p0": "44〜45",
         "p1": "44.0〜45.2",
         "count": "74〜76"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "48〜49",
         "p1": "48.2〜49.4",
         "count": "81〜83"
        },
        "unresolved": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "answered": {
         "p0": "48〜49",
         "p1": "48.2〜49.4",
         "count": "81〜83"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         159,
         159
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         9,
         9
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         9,
         9
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9464285714285714,
         0.9464285714285714
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.05357142857142857,
         0.05357142857142857
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.05357142857142857,
         0.05357142857142857
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "95",
         "p1": "94.6",
         "count": "159"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5",
         "p1": "5.4",
         "count": "9"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "5",
         "p1": "5.4",
         "count": "9"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         162,
         162
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9642857142857143,
         0.9642857142857143
        ],
        "abstain": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023809523809523808,
         0.023809523809523808
        ]
       },
       "disp": {
        "correct": {
         "p0": "96",
         "p1": "96.4",
         "count": "162"
        },
        "abstain": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         4,
         3
        ],
        "abstain": [
         129,
         130
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         35,
         35
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         35,
         35
        ]
       },
       "rates": {
        "correct": [
         0.023809523809523808,
         0.017857142857142856
        ],
        "abstain": [
         0.7678571428571429,
         0.7738095238095238
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.20833333333333334,
         0.20833333333333334
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.20833333333333334,
         0.20833333333333334
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        },
        "abstain": {
         "p0": "77",
         "p1": "76.8〜77.4",
         "count": "129〜130"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "21",
         "p1": "20.8",
         "count": "35"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "21",
         "p1": "20.8",
         "count": "35"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         164,
         164
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         4
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9761904761904762,
         0.9761904761904762
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023809523809523808,
         0.023809523809523808
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "98",
         "p1": "97.6",
         "count": "164"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         163,
         163
        ],
        "abstain": [
         1,
         1
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9702380952380952,
         0.9702380952380952
        ],
        "abstain": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023809523809523808,
         0.023809523809523808
        ]
       },
       "disp": {
        "correct": {
         "p0": "97",
         "p1": "97.0",
         "count": "163"
        },
        "abstain": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         5,
         5
        ],
        "abstain": [
         119,
         121
        ],
        "hedged": [
         1,
         0
        ],
        "other": [
         43,
         42
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         44,
         42
        ]
       },
       "rates": {
        "correct": [
         0.02976190476190476,
         0.02976190476190476
        ],
        "abstain": [
         0.7083333333333334,
         0.7202380952380952
        ],
        "hedged": [
         0.005952380952380952,
         0.0
        ],
        "other": [
         0.25595238095238093,
         0.25
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.2619047619047619,
         0.25
        ]
       },
       "disp": {
        "correct": {
         "p0": "3",
         "p1": "3.0",
         "count": "5"
        },
        "abstain": {
         "p0": "71〜72",
         "p1": "70.8〜72.0",
         "count": "119〜121"
        },
        "hedged": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        },
        "other": {
         "p0": "25〜26",
         "p1": "25.0〜25.6",
         "count": "42〜43"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "25〜26",
         "p1": "25.0〜26.2",
         "count": "42〜44"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         164,
         164
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         4
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9761904761904762,
         0.9761904761904762
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023809523809523808,
         0.023809523809523808
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "98",
         "p1": "97.6",
         "count": "164"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        }
       }
      }
     }
    },
    "gemma4:12b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         164,
         164
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9761904761904762,
         0.9761904761904762
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023809523809523808,
         0.023809523809523808
        ]
       },
       "disp": {
        "correct": {
         "p0": "98",
         "p1": "97.6",
         "count": "164"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         2,
         2
        ],
        "abstain": [
         105,
         106
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         59,
         59
        ],
        "unresolved": [
         2,
         1
        ],
        "answered": [
         59,
         59
        ]
       },
       "rates": {
        "correct": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "abstain": [
         0.625,
         0.6309523809523809
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.35119047619047616,
         0.35119047619047616
        ],
        "unresolved": [
         0.011904761904761904,
         0.005952380952380952
        ],
        "answered": [
         0.35119047619047616,
         0.35119047619047616
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "abstain": {
         "p0": "63",
         "p1": "62.5〜63.1",
         "count": "105〜106"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "35",
         "p1": "35.1",
         "count": "59"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.6〜1.2",
         "count": "1〜2"
        },
        "answered": {
         "p0": "35",
         "p1": "35.1",
         "count": "59"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         165,
         165
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         3
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9821428571428571,
         0.9821428571428571
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.017857142857142856,
         0.017857142857142856
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "98",
         "p1": "98.2",
         "count": "165"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         160,
         161
        ],
        "abstain": [
         5,
         4
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         3
        ]
       },
       "rates": {
        "correct": [
         0.9523809523809523,
         0.9583333333333334
        ],
        "abstain": [
         0.02976190476190476,
         0.023809523809523808
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.017857142857142856,
         0.017857142857142856
        ]
       },
       "disp": {
        "correct": {
         "p0": "95〜96",
         "p1": "95.2〜95.8",
         "count": "160〜161"
        },
        "abstain": {
         "p0": "2〜3",
         "p1": "2.4〜3.0",
         "count": "4〜5"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         147,
         146
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         20,
         21
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         20,
         21
        ]
       },
       "rates": {
        "correct": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "abstain": [
         0.875,
         0.8690476190476191
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.11904761904761904,
         0.125
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.11904761904761904,
         0.125
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "abstain": {
         "p0": "87〜88",
         "p1": "86.9〜87.5",
         "count": "146〜147"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "12〜13",
         "p1": "11.9〜12.5",
         "count": "20〜21"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "12〜13",
         "p1": "11.9〜12.5",
         "count": "20〜21"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         165,
         165
        ],
        "abstain": [
         3,
         3
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.9821428571428571,
         0.9821428571428571
        ],
        "abstain": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "98",
         "p1": "98.2",
         "count": "165"
        },
        "abstain": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         3,
         3
        ],
        "abstain": [
         140,
         141
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         25,
         24
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         25,
         24
        ]
       },
       "rates": {
        "correct": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "abstain": [
         0.8333333333333334,
         0.8392857142857143
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.1488095238095238,
         0.14285714285714285
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.1488095238095238,
         0.14285714285714285
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "abstain": {
         "p0": "83〜84",
         "p1": "83.3〜83.9",
         "count": "140〜141"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "14〜15",
         "p1": "14.3〜14.9",
         "count": "24〜25"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "14〜15",
         "p1": "14.3〜14.9",
         "count": "24〜25"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "gemma4:26b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         165,
         165
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.9821428571428571,
         0.9821428571428571
        ],
        "abstain": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "98",
         "p1": "98.2",
         "count": "165"
        },
        "abstain": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         4,
         4
        ],
        "abstain": [
         122,
         125
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         42,
         39
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         42,
         39
        ]
       },
       "rates": {
        "correct": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "abstain": [
         0.7261904761904762,
         0.7440476190476191
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.25,
         0.23214285714285715
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.25,
         0.23214285714285715
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "abstain": {
         "p0": "73〜74",
         "p1": "72.6〜74.4",
         "count": "122〜125"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "23〜25",
         "p1": "23.2〜25.0",
         "count": "39〜42"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "23〜25",
         "p1": "23.2〜25.0",
         "count": "39〜42"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         166,
         165
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         3
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9880952380952381,
         0.9821428571428571
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.011904761904761904,
         0.017857142857142856
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.011904761904761904,
         0.017857142857142856
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "98〜99",
         "p1": "98.2〜98.8",
         "count": "165〜166"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1〜2",
         "p1": "1.2〜1.8",
         "count": "2〜3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1〜2",
         "p1": "1.2〜1.8",
         "count": "2〜3"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         163,
         162
        ],
        "abstain": [
         3,
         4
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         2
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         2
        ]
       },
       "rates": {
        "correct": [
         0.9702380952380952,
         0.9642857142857143
        ],
        "abstain": [
         0.017857142857142856,
         0.023809523809523808
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.011904761904761904,
         0.011904761904761904
        ]
       },
       "disp": {
        "correct": {
         "p0": "96〜97",
         "p1": "96.4〜97.0",
         "count": "162〜163"
        },
        "abstain": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         2,
         2
        ],
        "abstain": [
         147,
         146
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         19,
         20
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         19,
         20
        ]
       },
       "rates": {
        "correct": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "abstain": [
         0.875,
         0.8690476190476191
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.1130952380952381,
         0.11904761904761904
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.1130952380952381,
         0.11904761904761904
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "abstain": {
         "p0": "87〜88",
         "p1": "86.9〜87.5",
         "count": "146〜147"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "11〜12",
         "p1": "11.3〜11.9",
         "count": "19〜20"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "11〜12",
         "p1": "11.3〜11.9",
         "count": "19〜20"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         165,
         165
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.9821428571428571,
         0.9821428571428571
        ],
        "abstain": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "98",
         "p1": "98.2",
         "count": "165"
        },
        "abstain": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         4,
         3
        ],
        "abstain": [
         147,
         147
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         16,
         17
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         16,
         17
        ]
       },
       "rates": {
        "correct": [
         0.023809523809523808,
         0.017857142857142856
        ],
        "abstain": [
         0.875,
         0.875
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.09523809523809523,
         0.10119047619047619
        ],
        "unresolved": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "answered": [
         0.09523809523809523,
         0.10119047619047619
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        },
        "abstain": {
         "p0": "88",
         "p1": "87.5",
         "count": "147"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "10",
         "p1": "9.5〜10.1",
         "count": "16〜17"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "answered": {
         "p0": "10",
         "p1": "9.5〜10.1",
         "count": "16〜17"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "gpt-oss:20b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         163,
         163
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         5,
         5
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         5,
         5
        ]
       },
       "rates": {
        "correct": [
         0.9702380952380952,
         0.9702380952380952
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.02976190476190476,
         0.02976190476190476
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.02976190476190476,
         0.02976190476190476
        ]
       },
       "disp": {
        "correct": {
         "p0": "97",
         "p1": "97.0",
         "count": "163"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3",
         "p1": "3.0",
         "count": "5"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3",
         "p1": "3.0",
         "count": "5"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         8,
         6
        ],
        "abstain": [
         26,
         24
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         134,
         138
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         134,
         138
        ]
       },
       "rates": {
        "correct": [
         0.047619047619047616,
         0.03571428571428571
        ],
        "abstain": [
         0.15476190476190477,
         0.14285714285714285
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.7976190476190477,
         0.8214285714285714
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.7976190476190477,
         0.8214285714285714
        ]
       },
       "disp": {
        "correct": {
         "p0": "4〜5",
         "p1": "3.6〜4.8",
         "count": "6〜8"
        },
        "abstain": {
         "p0": "14〜15",
         "p1": "14.3〜15.5",
         "count": "24〜26"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "80〜82",
         "p1": "79.8〜82.1",
         "count": "134〜138"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "80〜82",
         "p1": "79.8〜82.1",
         "count": "134〜138"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         9,
         10
        ],
        "abstain": [
         19,
         19
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         140,
         139
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         140,
         139
        ]
       },
       "rates": {
        "correct": [
         0.05357142857142857,
         0.05952380952380952
        ],
        "abstain": [
         0.1130952380952381,
         0.1130952380952381
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.8333333333333334,
         0.8273809523809523
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.8333333333333334,
         0.8273809523809523
        ]
       },
       "disp": {
        "correct": {
         "p0": "5〜6",
         "p1": "5.4〜6.0",
         "count": "9〜10"
        },
        "abstain": {
         "p0": "11",
         "p1": "11.3",
         "count": "19"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "83",
         "p1": "82.7〜83.3",
         "count": "139〜140"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "83",
         "p1": "82.7〜83.3",
         "count": "139〜140"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         162,
         162
        ],
        "abstain": [
         1,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         5,
         6
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         5,
         6
        ]
       },
       "rates": {
        "correct": [
         0.9642857142857143,
         0.9642857142857143
        ],
        "abstain": [
         0.005952380952380952,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.02976190476190476,
         0.03571428571428571
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.02976190476190476,
         0.03571428571428571
        ]
       },
       "disp": {
        "correct": {
         "p0": "96",
         "p1": "96.4",
         "count": "162"
        },
        "abstain": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3〜4",
         "p1": "3.0〜3.6",
         "count": "5〜6"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3〜4",
         "p1": "3.0〜3.6",
         "count": "5〜6"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         6,
         6
        ],
        "abstain": [
         116,
         116
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         46,
         46
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         46,
         46
        ]
       },
       "rates": {
        "correct": [
         0.03571428571428571,
         0.03571428571428571
        ],
        "abstain": [
         0.6904761904761905,
         0.6904761904761905
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.27380952380952384,
         0.27380952380952384
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.27380952380952384,
         0.27380952380952384
        ]
       },
       "disp": {
        "correct": {
         "p0": "4",
         "p1": "3.6",
         "count": "6"
        },
        "abstain": {
         "p0": "69",
         "p1": "69.0",
         "count": "116"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "27",
         "p1": "27.4",
         "count": "46"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "27",
         "p1": "27.4",
         "count": "46"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         161,
         162
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         6,
         5
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         6,
         5
        ]
       },
       "rates": {
        "correct": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "abstain": [
         0.9583333333333334,
         0.9642857142857143
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.03571428571428571,
         0.02976190476190476
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.03571428571428571,
         0.02976190476190476
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "abstain": {
         "p0": "96",
         "p1": "95.8〜96.4",
         "count": "161〜162"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3〜4",
         "p1": "3.0〜3.6",
         "count": "5〜6"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3〜4",
         "p1": "3.0〜3.6",
         "count": "5〜6"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         164,
         163
        ],
        "abstain": [
         1,
         1
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9761904761904762,
         0.9702380952380952
        ],
        "abstain": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.017857142857142856,
         0.023809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.017857142857142856,
         0.023809523809523808
        ]
       },
       "disp": {
        "correct": {
         "p0": "97〜98",
         "p1": "97.0〜97.6",
         "count": "163〜164"
        },
        "abstain": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         4,
         4
        ],
        "abstain": [
         117,
         118
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         46,
         45
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         46,
         45
        ]
       },
       "rates": {
        "correct": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "abstain": [
         0.6964285714285714,
         0.7023809523809523
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.27380952380952384,
         0.26785714285714285
        ],
        "unresolved": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "answered": [
         0.27380952380952384,
         0.26785714285714285
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "abstain": {
         "p0": "70",
         "p1": "69.6〜70.2",
         "count": "117〜118"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "27",
         "p1": "26.8〜27.4",
         "count": "45〜46"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "answered": {
         "p0": "27",
         "p1": "26.8〜27.4",
         "count": "45〜46"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         167,
         167
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9940476190476191,
         0.9940476190476191
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "99.4",
         "count": "167"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      }
     }
    },
    "gpt-oss:120b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         165,
         163
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         5
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         5
        ]
       },
       "rates": {
        "correct": [
         0.9821428571428571,
         0.9702380952380952
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.017857142857142856,
         0.02976190476190476
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.017857142857142856,
         0.02976190476190476
        ]
       },
       "disp": {
        "correct": {
         "p0": "97〜98",
         "p1": "97.0〜98.2",
         "count": "163〜165"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2〜3",
         "p1": "1.8〜3.0",
         "count": "3〜5"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2〜3",
         "p1": "1.8〜3.0",
         "count": "3〜5"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         13,
         10
        ],
        "abstain": [
         35,
         35
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         120,
         123
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         120,
         123
        ]
       },
       "rates": {
        "correct": [
         0.07738095238095238,
         0.05952380952380952
        ],
        "abstain": [
         0.20833333333333334,
         0.20833333333333334
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.7142857142857143,
         0.7321428571428571
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.7142857142857143,
         0.7321428571428571
        ]
       },
       "disp": {
        "correct": {
         "p0": "6〜8",
         "p1": "6.0〜7.7",
         "count": "10〜13"
        },
        "abstain": {
         "p0": "21",
         "p1": "20.8",
         "count": "35"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "71〜73",
         "p1": "71.4〜73.2",
         "count": "120〜123"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "71〜73",
         "p1": "71.4〜73.2",
         "count": "120〜123"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         12,
         10
        ],
        "abstain": [
         45,
         44
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         111,
         114
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         111,
         114
        ]
       },
       "rates": {
        "correct": [
         0.07142857142857142,
         0.05952380952380952
        ],
        "abstain": [
         0.26785714285714285,
         0.2619047619047619
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.6607142857142857,
         0.6785714285714286
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.6607142857142857,
         0.6785714285714286
        ]
       },
       "disp": {
        "correct": {
         "p0": "6〜7",
         "p1": "6.0〜7.1",
         "count": "10〜12"
        },
        "abstain": {
         "p0": "26〜27",
         "p1": "26.2〜26.8",
         "count": "44〜45"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "66〜68",
         "p1": "66.1〜67.9",
         "count": "111〜114"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "66〜68",
         "p1": "66.1〜67.9",
         "count": "111〜114"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         164,
         163
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         3
        ]
       },
       "rates": {
        "correct": [
         0.9761904761904762,
         0.9702380952380952
        ],
        "abstain": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.011904761904761904,
         0.017857142857142856
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.011904761904761904,
         0.017857142857142856
        ]
       },
       "disp": {
        "correct": {
         "p0": "97〜98",
         "p1": "97.0〜97.6",
         "count": "163〜164"
        },
        "abstain": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1〜2",
         "p1": "1.2〜1.8",
         "count": "2〜3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1〜2",
         "p1": "1.2〜1.8",
         "count": "2〜3"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         3,
         4
        ],
        "abstain": [
         150,
         148
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         15,
         16
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         15,
         16
        ]
       },
       "rates": {
        "correct": [
         0.017857142857142856,
         0.023809523809523808
        ],
        "abstain": [
         0.8928571428571429,
         0.8809523809523809
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.08928571428571429,
         0.09523809523809523
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.08928571428571429,
         0.09523809523809523
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        },
        "abstain": {
         "p0": "88〜89",
         "p1": "88.1〜89.3",
         "count": "148〜150"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "9〜10",
         "p1": "8.9〜9.5",
         "count": "15〜16"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "9〜10",
         "p1": "8.9〜9.5",
         "count": "15〜16"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         167,
         166
        ],
        "abstain": [
         1,
         1
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         1
        ]
       },
       "rates": {
        "correct": [
         0.9940476190476191,
         0.9880952380952381
        ],
        "abstain": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "99",
         "p1": "98.8〜99.4",
         "count": "166〜167"
        },
        "abstain": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         3,
         4
        ],
        "abstain": [
         144,
         146
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         21,
         17
        ],
        "unresolved": [
         0,
         1
        ],
        "answered": [
         21,
         17
        ]
       },
       "rates": {
        "correct": [
         0.017857142857142856,
         0.023809523809523808
        ],
        "abstain": [
         0.8571428571428571,
         0.8690476190476191
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.125,
         0.10119047619047619
        ],
        "unresolved": [
         0.0,
         0.005952380952380952
        ],
        "answered": [
         0.125,
         0.10119047619047619
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        },
        "abstain": {
         "p0": "86〜87",
         "p1": "85.7〜86.9",
         "count": "144〜146"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "10〜13",
         "p1": "10.1〜12.5",
         "count": "17〜21"
        },
        "unresolved": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        },
        "answered": {
         "p0": "10〜13",
         "p1": "10.1〜12.5",
         "count": "17〜21"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         167
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         0.9940476190476191
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99〜100",
         "p1": "99.4〜100.0",
         "count": "167〜168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        }
       }
      }
     }
    },
    "deepseek-r1:8b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         137,
         141
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         16,
         17
        ],
        "unresolved": [
         13,
         8
        ],
        "answered": [
         16,
         17
        ]
       },
       "rates": {
        "correct": [
         0.8154761904761905,
         0.8392857142857143
        ],
        "abstain": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.09523809523809523,
         0.10119047619047619
        ],
        "unresolved": [
         0.07738095238095238,
         0.047619047619047616
        ],
        "answered": [
         0.09523809523809523,
         0.10119047619047619
        ]
       },
       "disp": {
        "correct": {
         "p0": "82〜84",
         "p1": "81.5〜83.9",
         "count": "137〜141"
        },
        "abstain": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "10",
         "p1": "9.5〜10.1",
         "count": "16〜17"
        },
        "unresolved": {
         "p0": "5〜8",
         "p1": "4.8〜7.7",
         "count": "8〜13"
        },
        "answered": {
         "p0": "10",
         "p1": "9.5〜10.1",
         "count": "16〜17"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         4,
         3
        ],
        "abstain": [
         62,
         61
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         71,
         69
        ],
        "unresolved": [
         31,
         35
        ],
        "answered": [
         71,
         69
        ]
       },
       "rates": {
        "correct": [
         0.023809523809523808,
         0.017857142857142856
        ],
        "abstain": [
         0.36904761904761907,
         0.3630952380952381
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.4226190476190476,
         0.4107142857142857
        ],
        "unresolved": [
         0.18452380952380953,
         0.20833333333333334
        ],
        "answered": [
         0.4226190476190476,
         0.4107142857142857
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        },
        "abstain": {
         "p0": "36〜37",
         "p1": "36.3〜36.9",
         "count": "61〜62"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "41〜42",
         "p1": "41.1〜42.3",
         "count": "69〜71"
        },
        "unresolved": {
         "p0": "18〜21",
         "p1": "18.5〜20.8",
         "count": "31〜35"
        },
        "answered": {
         "p0": "41〜42",
         "p1": "41.1〜42.3",
         "count": "69〜71"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         137,
         128
        ],
        "hedged": [
         1,
         0
        ],
        "other": [
         14,
         21
        ],
        "unresolved": [
         16,
         19
        ],
        "answered": [
         15,
         21
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.8154761904761905,
         0.7619047619047619
        ],
        "hedged": [
         0.005952380952380952,
         0.0
        ],
        "other": [
         0.08333333333333333,
         0.125
        ],
        "unresolved": [
         0.09523809523809523,
         0.1130952380952381
        ],
        "answered": [
         0.08928571428571429,
         0.125
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "76〜82",
         "p1": "76.2〜81.5",
         "count": "128〜137"
        },
        "hedged": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        },
        "other": {
         "p0": "8〜13",
         "p1": "8.3〜12.5",
         "count": "14〜21"
        },
        "unresolved": {
         "p0": "10〜11",
         "p1": "9.5〜11.3",
         "count": "16〜19"
        },
        "answered": {
         "p0": "9〜13",
         "p1": "8.9〜12.5",
         "count": "15〜21"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         136,
         128
        ],
        "abstain": [
         13,
         20
        ],
        "hedged": [
         1,
         0
        ],
        "other": [
         9,
         14
        ],
        "unresolved": [
         9,
         6
        ],
        "answered": [
         10,
         14
        ]
       },
       "rates": {
        "correct": [
         0.8095238095238095,
         0.7619047619047619
        ],
        "abstain": [
         0.07738095238095238,
         0.11904761904761904
        ],
        "hedged": [
         0.005952380952380952,
         0.0
        ],
        "other": [
         0.05357142857142857,
         0.08333333333333333
        ],
        "unresolved": [
         0.05357142857142857,
         0.03571428571428571
        ],
        "answered": [
         0.05952380952380952,
         0.08333333333333333
        ]
       },
       "disp": {
        "correct": {
         "p0": "76〜81",
         "p1": "76.2〜81.0",
         "count": "128〜136"
        },
        "abstain": {
         "p0": "8〜12",
         "p1": "7.7〜11.9",
         "count": "13〜20"
        },
        "hedged": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        },
        "other": {
         "p0": "5〜8",
         "p1": "5.4〜8.3",
         "count": "9〜14"
        },
        "unresolved": {
         "p0": "4〜5",
         "p1": "3.6〜5.4",
         "count": "6〜9"
        },
        "answered": {
         "p0": "6〜8",
         "p1": "6.0〜8.3",
         "count": "10〜14"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         1,
         2
        ],
        "abstain": [
         132,
         127
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         25,
         23
        ],
        "unresolved": [
         10,
         16
        ],
        "answered": [
         25,
         23
        ]
       },
       "rates": {
        "correct": [
         0.005952380952380952,
         0.011904761904761904
        ],
        "abstain": [
         0.7857142857142857,
         0.7559523809523809
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.1488095238095238,
         0.13690476190476192
        ],
        "unresolved": [
         0.05952380952380952,
         0.09523809523809523
        ],
        "answered": [
         0.1488095238095238,
         0.13690476190476192
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.6〜1.2",
         "count": "1〜2"
        },
        "abstain": {
         "p0": "76〜79",
         "p1": "75.6〜78.6",
         "count": "127〜132"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "14〜15",
         "p1": "13.7〜14.9",
         "count": "23〜25"
        },
        "unresolved": {
         "p0": "6〜10",
         "p1": "6.0〜9.5",
         "count": "10〜16"
        },
        "answered": {
         "p0": "14〜15",
         "p1": "13.7〜14.9",
         "count": "23〜25"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         166,
         162
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         3
        ],
        "unresolved": [
         2,
         3
        ],
        "answered": [
         0,
         3
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9880952380952381,
         0.9642857142857143
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.017857142857142856
        ],
        "unresolved": [
         0.011904761904761904,
         0.017857142857142856
        ],
        "answered": [
         0.0,
         0.017857142857142856
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "96〜99",
         "p1": "96.4〜98.8",
         "count": "162〜166"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0〜2",
         "p1": "0.0〜1.8",
         "count": "0〜3"
        },
        "unresolved": {
         "p0": "1〜2",
         "p1": "1.2〜1.8",
         "count": "2〜3"
        },
        "answered": {
         "p0": "0〜2",
         "p1": "0.0〜1.8",
         "count": "0〜3"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         140,
         144
        ],
        "abstain": [
         9,
         12
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         10,
         7
        ],
        "unresolved": [
         9,
         5
        ],
        "answered": [
         10,
         7
        ]
       },
       "rates": {
        "correct": [
         0.8333333333333334,
         0.8571428571428571
        ],
        "abstain": [
         0.05357142857142857,
         0.07142857142857142
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.05952380952380952,
         0.041666666666666664
        ],
        "unresolved": [
         0.05357142857142857,
         0.02976190476190476
        ],
        "answered": [
         0.05952380952380952,
         0.041666666666666664
        ]
       },
       "disp": {
        "correct": {
         "p0": "83〜86",
         "p1": "83.3〜85.7",
         "count": "140〜144"
        },
        "abstain": {
         "p0": "5〜7",
         "p1": "5.4〜7.1",
         "count": "9〜12"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4〜6",
         "p1": "4.2〜6.0",
         "count": "7〜10"
        },
        "unresolved": {
         "p0": "3〜5",
         "p1": "3.0〜5.4",
         "count": "5〜9"
        },
        "answered": {
         "p0": "4〜6",
         "p1": "4.2〜6.0",
         "count": "7〜10"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         1,
         2
        ],
        "abstain": [
         129,
         132
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         19,
         18
        ],
        "unresolved": [
         19,
         16
        ],
        "answered": [
         19,
         18
        ]
       },
       "rates": {
        "correct": [
         0.005952380952380952,
         0.011904761904761904
        ],
        "abstain": [
         0.7678571428571429,
         0.7857142857142857
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.1130952380952381,
         0.10714285714285714
        ],
        "unresolved": [
         0.1130952380952381,
         0.09523809523809523
        ],
        "answered": [
         0.1130952380952381,
         0.10714285714285714
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.6〜1.2",
         "count": "1〜2"
        },
        "abstain": {
         "p0": "77〜79",
         "p1": "76.8〜78.6",
         "count": "129〜132"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "11",
         "p1": "10.7〜11.3",
         "count": "18〜19"
        },
        "unresolved": {
         "p0": "10〜11",
         "p1": "9.5〜11.3",
         "count": "16〜19"
        },
        "answered": {
         "p0": "11",
         "p1": "10.7〜11.3",
         "count": "18〜19"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         163,
         166
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         4,
         1
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9702380952380952,
         0.9880952380952381
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.023809523809523808,
         0.005952380952380952
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "97〜99",
         "p1": "97.0〜98.8",
         "count": "163〜166"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "1〜2",
         "p1": "0.6〜2.4",
         "count": "1〜4"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      }
     }
    },
    "deepseek-r1:14b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         159,
         156
        ],
        "abstain": [
         0,
         1
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         8,
         10
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         8,
         10
        ]
       },
       "rates": {
        "correct": [
         0.9464285714285714,
         0.9285714285714286
        ],
        "abstain": [
         0.0,
         0.005952380952380952
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.047619047619047616,
         0.05952380952380952
        ],
        "unresolved": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "answered": [
         0.047619047619047616,
         0.05952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "93〜95",
         "p1": "92.9〜94.6",
         "count": "156〜159"
        },
        "abstain": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5〜6",
         "p1": "4.8〜6.0",
         "count": "8〜10"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "answered": {
         "p0": "5〜6",
         "p1": "4.8〜6.0",
         "count": "8〜10"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         5,
         5
        ],
        "abstain": [
         67,
         69
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         92,
         90
        ],
        "unresolved": [
         4,
         4
        ],
        "answered": [
         92,
         90
        ]
       },
       "rates": {
        "correct": [
         0.02976190476190476,
         0.02976190476190476
        ],
        "abstain": [
         0.39880952380952384,
         0.4107142857142857
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.5476190476190477,
         0.5357142857142857
        ],
        "unresolved": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "answered": [
         0.5476190476190477,
         0.5357142857142857
        ]
       },
       "disp": {
        "correct": {
         "p0": "3",
         "p1": "3.0",
         "count": "5"
        },
        "abstain": {
         "p0": "40〜41",
         "p1": "39.9〜41.1",
         "count": "67〜69"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "54〜55",
         "p1": "53.6〜54.8",
         "count": "90〜92"
        },
        "unresolved": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "answered": {
         "p0": "54〜55",
         "p1": "53.6〜54.8",
         "count": "90〜92"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         2
        ],
        "abstain": [
         148,
         145
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         20,
         21
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         20,
         21
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.011904761904761904
        ],
        "abstain": [
         0.8809523809523809,
         0.8630952380952381
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.11904761904761904,
         0.125
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.11904761904761904,
         0.125
        ]
       },
       "disp": {
        "correct": {
         "p0": "0〜1",
         "p1": "0.0〜1.2",
         "count": "0〜2"
        },
        "abstain": {
         "p0": "86〜88",
         "p1": "86.3〜88.1",
         "count": "145〜148"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "12〜13",
         "p1": "11.9〜12.5",
         "count": "20〜21"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "12〜13",
         "p1": "11.9〜12.5",
         "count": "20〜21"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         157,
         158
        ],
        "abstain": [
         6,
         6
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         5,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         5,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9345238095238095,
         0.9404761904761905
        ],
        "abstain": [
         0.03571428571428571,
         0.03571428571428571
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.02976190476190476,
         0.023809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.02976190476190476,
         0.023809523809523808
        ]
       },
       "disp": {
        "correct": {
         "p0": "93〜94",
         "p1": "93.5〜94.0",
         "count": "157〜158"
        },
        "abstain": {
         "p0": "4",
         "p1": "3.6",
         "count": "6"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2〜3",
         "p1": "2.4〜3.0",
         "count": "4〜5"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2〜3",
         "p1": "2.4〜3.0",
         "count": "4〜5"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         3,
         3
        ],
        "abstain": [
         140,
         140
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         25,
         25
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         25,
         25
        ]
       },
       "rates": {
        "correct": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "abstain": [
         0.8333333333333334,
         0.8333333333333334
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.1488095238095238,
         0.1488095238095238
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.1488095238095238,
         0.1488095238095238
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "abstain": {
         "p0": "83",
         "p1": "83.3",
         "count": "140"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "15",
         "p1": "14.9",
         "count": "25"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "15",
         "p1": "14.9",
         "count": "25"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         166,
         166
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         2
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         2
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9880952380952381,
         0.9880952380952381
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.011904761904761904,
         0.011904761904761904
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "98.8",
         "count": "166"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         157,
         159
        ],
        "abstain": [
         6,
         4
        ],
        "hedged": [
         0,
         1
        ],
        "other": [
         5,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         5,
         5
        ]
       },
       "rates": {
        "correct": [
         0.9345238095238095,
         0.9464285714285714
        ],
        "abstain": [
         0.03571428571428571,
         0.023809523809523808
        ],
        "hedged": [
         0.0,
         0.005952380952380952
        ],
        "other": [
         0.02976190476190476,
         0.023809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.02976190476190476,
         0.02976190476190476
        ]
       },
       "disp": {
        "correct": {
         "p0": "93〜95",
         "p1": "93.5〜94.6",
         "count": "157〜159"
        },
        "abstain": {
         "p0": "2〜4",
         "p1": "2.4〜3.6",
         "count": "4〜6"
        },
        "hedged": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        },
        "other": {
         "p0": "2〜3",
         "p1": "2.4〜3.0",
         "count": "4〜5"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3",
         "p1": "3.0",
         "count": "5"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         4,
         4
        ],
        "abstain": [
         135,
         132
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         29,
         32
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         29,
         32
        ]
       },
       "rates": {
        "correct": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "abstain": [
         0.8035714285714286,
         0.7857142857142857
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.17261904761904762,
         0.19047619047619047
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.17261904761904762,
         0.19047619047619047
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "abstain": {
         "p0": "79〜80",
         "p1": "78.6〜80.4",
         "count": "132〜135"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "17〜19",
         "p1": "17.3〜19.0",
         "count": "29〜32"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "17〜19",
         "p1": "17.3〜19.0",
         "count": "29〜32"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         167,
         167
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9940476190476191,
         0.9940476190476191
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.005952380952380952,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "99.4",
         "count": "167"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        }
       }
      }
     }
    },
    "llama3.1:8b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         159,
         160
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         9,
         8
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         9,
         8
        ]
       },
       "rates": {
        "correct": [
         0.9464285714285714,
         0.9523809523809523
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.05357142857142857,
         0.047619047619047616
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.05357142857142857,
         0.047619047619047616
        ]
       },
       "disp": {
        "correct": {
         "p0": "95",
         "p1": "94.6〜95.2",
         "count": "159〜160"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5",
         "p1": "4.8〜5.4",
         "count": "8〜9"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "5",
         "p1": "4.8〜5.4",
         "count": "8〜9"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         2,
         2
        ],
        "abstain": [
         27,
         28
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         135,
         135
        ],
        "unresolved": [
         4,
         3
        ],
        "answered": [
         135,
         135
        ]
       },
       "rates": {
        "correct": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "abstain": [
         0.16071428571428573,
         0.16666666666666666
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.8035714285714286,
         0.8035714285714286
        ],
        "unresolved": [
         0.023809523809523808,
         0.017857142857142856
        ],
        "answered": [
         0.8035714285714286,
         0.8035714285714286
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "abstain": {
         "p0": "16〜17",
         "p1": "16.1〜16.7",
         "count": "27〜28"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "80",
         "p1": "80.4",
         "count": "135"
        },
        "unresolved": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        },
        "answered": {
         "p0": "80",
         "p1": "80.4",
         "count": "135"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         85,
         82
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         79,
         80
        ],
        "unresolved": [
         3,
         5
        ],
        "answered": [
         79,
         80
        ]
       },
       "rates": {
        "correct": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "abstain": [
         0.5059523809523809,
         0.4880952380952381
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.47023809523809523,
         0.47619047619047616
        ],
        "unresolved": [
         0.017857142857142856,
         0.02976190476190476
        ],
        "answered": [
         0.47023809523809523,
         0.47619047619047616
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "abstain": {
         "p0": "49〜51",
         "p1": "48.8〜50.6",
         "count": "82〜85"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "47〜48",
         "p1": "47.0〜47.6",
         "count": "79〜80"
        },
        "unresolved": {
         "p0": "2〜3",
         "p1": "1.8〜3.0",
         "count": "3〜5"
        },
        "answered": {
         "p0": "47〜48",
         "p1": "47.0〜47.6",
         "count": "79〜80"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         140,
         139
        ],
        "abstain": [
         8,
         8
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         15,
         14
        ],
        "unresolved": [
         5,
         7
        ],
        "answered": [
         15,
         14
        ]
       },
       "rates": {
        "correct": [
         0.8333333333333334,
         0.8273809523809523
        ],
        "abstain": [
         0.047619047619047616,
         0.047619047619047616
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.08928571428571429,
         0.08333333333333333
        ],
        "unresolved": [
         0.02976190476190476,
         0.041666666666666664
        ],
        "answered": [
         0.08928571428571429,
         0.08333333333333333
        ]
       },
       "disp": {
        "correct": {
         "p0": "83",
         "p1": "82.7〜83.3",
         "count": "139〜140"
        },
        "abstain": {
         "p0": "5",
         "p1": "4.8",
         "count": "8"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "8〜9",
         "p1": "8.3〜8.9",
         "count": "14〜15"
        },
        "unresolved": {
         "p0": "3〜4",
         "p1": "3.0〜4.2",
         "count": "5〜7"
        },
        "answered": {
         "p0": "8〜9",
         "p1": "8.3〜8.9",
         "count": "14〜15"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         119,
         118
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         28,
         27
        ],
        "unresolved": [
         20,
         22
        ],
        "answered": [
         28,
         27
        ]
       },
       "rates": {
        "correct": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "abstain": [
         0.7083333333333334,
         0.7023809523809523
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.16666666666666666,
         0.16071428571428573
        ],
        "unresolved": [
         0.11904761904761904,
         0.13095238095238096
        ],
        "answered": [
         0.16666666666666666,
         0.16071428571428573
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "abstain": {
         "p0": "70〜71",
         "p1": "70.2〜70.8",
         "count": "118〜119"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "16〜17",
         "p1": "16.1〜16.7",
         "count": "27〜28"
        },
        "unresolved": {
         "p0": "12〜13",
         "p1": "11.9〜13.1",
         "count": "20〜22"
        },
        "answered": {
         "p0": "16〜17",
         "p1": "16.1〜16.7",
         "count": "27〜28"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         165,
         165
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         1
        ],
        "unresolved": [
         3,
         2
        ],
        "answered": [
         0,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9821428571428571,
         0.9821428571428571
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.005952380952380952
        ],
        "unresolved": [
         0.017857142857142856,
         0.011904761904761904
        ],
        "answered": [
         0.0,
         0.005952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "98",
         "p1": "98.2",
         "count": "165"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        },
        "unresolved": {
         "p0": "1〜2",
         "p1": "1.2〜1.8",
         "count": "2〜3"
        },
        "answered": {
         "p0": "0〜1",
         "p1": "0.0〜0.6",
         "count": "0〜1"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         147,
         146
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         18,
         19
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         18,
         19
        ]
       },
       "rates": {
        "correct": [
         0.875,
         0.8690476190476191
        ],
        "abstain": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.10714285714285714,
         0.1130952380952381
        ],
        "unresolved": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "answered": [
         0.10714285714285714,
         0.1130952380952381
        ]
       },
       "disp": {
        "correct": {
         "p0": "87〜88",
         "p1": "86.9〜87.5",
         "count": "146〜147"
        },
        "abstain": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "11",
         "p1": "10.7〜11.3",
         "count": "18〜19"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "answered": {
         "p0": "11",
         "p1": "10.7〜11.3",
         "count": "18〜19"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         4,
         4
        ],
        "abstain": [
         54,
         56
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         107,
         102
        ],
        "unresolved": [
         3,
         6
        ],
        "answered": [
         107,
         102
        ]
       },
       "rates": {
        "correct": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "abstain": [
         0.32142857142857145,
         0.3333333333333333
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.6369047619047619,
         0.6071428571428571
        ],
        "unresolved": [
         0.017857142857142856,
         0.03571428571428571
        ],
        "answered": [
         0.6369047619047619,
         0.6071428571428571
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "abstain": {
         "p0": "32〜33",
         "p1": "32.1〜33.3",
         "count": "54〜56"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "61〜64",
         "p1": "60.7〜63.7",
         "count": "102〜107"
        },
        "unresolved": {
         "p0": "2〜4",
         "p1": "1.8〜3.6",
         "count": "3〜6"
        },
        "answered": {
         "p0": "61〜64",
         "p1": "60.7〜63.7",
         "count": "102〜107"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         117,
         121
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         48,
         44
        ],
        "unresolved": [
         3,
         3
        ],
        "answered": [
         48,
         44
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.6964285714285714,
         0.7202380952380952
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.2857142857142857,
         0.2619047619047619
        ],
        "unresolved": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "answered": [
         0.2857142857142857,
         0.2619047619047619
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "70〜72",
         "p1": "69.6〜72.0",
         "count": "117〜121"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "26〜29",
         "p1": "26.2〜28.6",
         "count": "44〜48"
        },
        "unresolved": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "answered": {
         "p0": "26〜29",
         "p1": "26.2〜28.6",
         "count": "44〜48"
        }
       }
      }
     }
    },
    "mistral-small3.2:24b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         162,
         162
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         6,
         6
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         6,
         6
        ]
       },
       "rates": {
        "correct": [
         0.9642857142857143,
         0.9642857142857143
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.03571428571428571,
         0.03571428571428571
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.03571428571428571,
         0.03571428571428571
        ]
       },
       "disp": {
        "correct": {
         "p0": "96",
         "p1": "96.4",
         "count": "162"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4",
         "p1": "3.6",
         "count": "6"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "4",
         "p1": "3.6",
         "count": "6"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         3,
         3
        ],
        "abstain": [
         65,
         63
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         100,
         102
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         100,
         102
        ]
       },
       "rates": {
        "correct": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "abstain": [
         0.3869047619047619,
         0.375
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.5952380952380952,
         0.6071428571428571
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.5952380952380952,
         0.6071428571428571
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "abstain": {
         "p0": "38〜39",
         "p1": "37.5〜38.7",
         "count": "63〜65"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "60〜61",
         "p1": "59.5〜60.7",
         "count": "100〜102"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "60〜61",
         "p1": "59.5〜60.7",
         "count": "100〜102"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         151,
         151
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         16,
         16
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         16,
         16
        ]
       },
       "rates": {
        "correct": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "abstain": [
         0.8988095238095238,
         0.8988095238095238
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.09523809523809523,
         0.09523809523809523
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.09523809523809523,
         0.09523809523809523
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "abstain": {
         "p0": "90",
         "p1": "89.9",
         "count": "151"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "10",
         "p1": "9.5",
         "count": "16"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "10",
         "p1": "9.5",
         "count": "16"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         160,
         160
        ],
        "abstain": [
         4,
         4
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9523809523809523,
         0.9523809523809523
        ],
        "abstain": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023809523809523808,
         0.023809523809523808
        ]
       },
       "disp": {
        "correct": {
         "p0": "95",
         "p1": "95.2",
         "count": "160"
        },
        "abstain": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         3,
         3
        ],
        "abstain": [
         137,
         137
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         28,
         28
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         28,
         28
        ]
       },
       "rates": {
        "correct": [
         0.017857142857142856,
         0.017857142857142856
        ],
        "abstain": [
         0.8154761904761905,
         0.8154761904761905
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.16666666666666666,
         0.16666666666666666
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.16666666666666666,
         0.16666666666666666
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.8",
         "count": "3"
        },
        "abstain": {
         "p0": "82",
         "p1": "81.5",
         "count": "137"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "17",
         "p1": "16.7",
         "count": "28"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "17",
         "p1": "16.7",
         "count": "28"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         162,
         162
        ],
        "abstain": [
         1,
         1
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         5,
         5
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         5,
         5
        ]
       },
       "rates": {
        "correct": [
         0.9642857142857143,
         0.9642857142857143
        ],
        "abstain": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.02976190476190476,
         0.02976190476190476
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.02976190476190476,
         0.02976190476190476
        ]
       },
       "disp": {
        "correct": {
         "p0": "96",
         "p1": "96.4",
         "count": "162"
        },
        "abstain": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3",
         "p1": "3.0",
         "count": "5"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3",
         "p1": "3.0",
         "count": "5"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         2,
         2
        ],
        "abstain": [
         132,
         132
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         33,
         33
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         33,
         33
        ]
       },
       "rates": {
        "correct": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "abstain": [
         0.7857142857142857,
         0.7857142857142857
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.19642857142857142,
         0.19642857142857142
        ],
        "unresolved": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "answered": [
         0.19642857142857142,
         0.19642857142857142
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "abstain": {
         "p0": "79",
         "p1": "78.6",
         "count": "132"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "20",
         "p1": "19.6",
         "count": "33"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "answered": {
         "p0": "20",
         "p1": "19.6",
         "count": "33"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "phi4:14b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         162,
         162
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         6,
         6
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         6,
         6
        ]
       },
       "rates": {
        "correct": [
         0.9642857142857143,
         0.9642857142857143
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.03571428571428571,
         0.03571428571428571
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.03571428571428571,
         0.03571428571428571
        ]
       },
       "disp": {
        "correct": {
         "p0": "96",
         "p1": "96.4",
         "count": "162"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4",
         "p1": "3.6",
         "count": "6"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "4",
         "p1": "3.6",
         "count": "6"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         4,
         4
        ],
        "abstain": [
         96,
         98
        ],
        "hedged": [
         2,
         2
        ],
        "other": [
         66,
         64
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         68,
         66
        ]
       },
       "rates": {
        "correct": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "abstain": [
         0.5714285714285714,
         0.5833333333333334
        ],
        "hedged": [
         0.011904761904761904,
         0.011904761904761904
        ],
        "other": [
         0.39285714285714285,
         0.38095238095238093
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.40476190476190477,
         0.39285714285714285
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "abstain": {
         "p0": "57〜58",
         "p1": "57.1〜58.3",
         "count": "96〜98"
        },
        "hedged": {
         "p0": "1",
         "p1": "1.2",
         "count": "2"
        },
        "other": {
         "p0": "38〜39",
         "p1": "38.1〜39.3",
         "count": "64〜66"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "39〜40",
         "p1": "39.3〜40.5",
         "count": "66〜68"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         162,
         161
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         5,
         6
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         5,
         6
        ]
       },
       "rates": {
        "correct": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "abstain": [
         0.9642857142857143,
         0.9583333333333334
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.02976190476190476,
         0.03571428571428571
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.02976190476190476,
         0.03571428571428571
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "abstain": {
         "p0": "96",
         "p1": "95.8〜96.4",
         "count": "161〜162"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3〜4",
         "p1": "3.0〜3.6",
         "count": "5〜6"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3〜4",
         "p1": "3.0〜3.6",
         "count": "5〜6"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         148,
         147
        ],
        "abstain": [
         16,
         16
        ],
        "hedged": [
         1,
         1
        ],
        "other": [
         3,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         5
        ]
       },
       "rates": {
        "correct": [
         0.8809523809523809,
         0.875
        ],
        "abstain": [
         0.09523809523809523,
         0.09523809523809523
        ],
        "hedged": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "other": [
         0.017857142857142856,
         0.023809523809523808
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023809523809523808,
         0.02976190476190476
        ]
       },
       "disp": {
        "correct": {
         "p0": "88",
         "p1": "87.5〜88.1",
         "count": "147〜148"
        },
        "abstain": {
         "p0": "10",
         "p1": "9.5",
         "count": "16"
        },
        "hedged": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "other": {
         "p0": "2",
         "p1": "1.8〜2.4",
         "count": "3〜4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2〜3",
         "p1": "2.4〜3.0",
         "count": "4〜5"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         155,
         155
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         12,
         12
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         12,
         12
        ]
       },
       "rates": {
        "correct": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "abstain": [
         0.9226190476190477,
         0.9226190476190477
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.07142857142857142,
         0.07142857142857142
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.07142857142857142,
         0.07142857142857142
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "abstain": {
         "p0": "92",
         "p1": "92.3",
         "count": "155"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "7",
         "p1": "7.1",
         "count": "12"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "7",
         "p1": "7.1",
         "count": "12"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         151,
         150
        ],
        "abstain": [
         7,
         7
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         9,
         10
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         9,
         10
        ]
       },
       "rates": {
        "correct": [
         0.8988095238095238,
         0.8928571428571429
        ],
        "abstain": [
         0.041666666666666664,
         0.041666666666666664
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.05357142857142857,
         0.05952380952380952
        ],
        "unresolved": [
         0.005952380952380952,
         0.005952380952380952
        ],
        "answered": [
         0.05357142857142857,
         0.05952380952380952
        ]
       },
       "disp": {
        "correct": {
         "p0": "89〜90",
         "p1": "89.3〜89.9",
         "count": "150〜151"
        },
        "abstain": {
         "p0": "4",
         "p1": "4.2",
         "count": "7"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5〜6",
         "p1": "5.4〜6.0",
         "count": "9〜10"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.6",
         "count": "1"
        },
        "answered": {
         "p0": "5〜6",
         "p1": "5.4〜6.0",
         "count": "9〜10"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         4,
         4
        ],
        "abstain": [
         152,
         153
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         12,
         11
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         12,
         11
        ]
       },
       "rates": {
        "correct": [
         0.023809523809523808,
         0.023809523809523808
        ],
        "abstain": [
         0.9047619047619048,
         0.9107142857142857
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.07142857142857142,
         0.06547619047619048
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.07142857142857142,
         0.06547619047619048
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "2.4",
         "count": "4"
        },
        "abstain": {
         "p0": "90〜91",
         "p1": "90.5〜91.1",
         "count": "152〜153"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "7",
         "p1": "6.5〜7.1",
         "count": "11〜12"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "7",
         "p1": "6.5〜7.1",
         "count": "11〜12"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        168,
        168
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         168,
         168
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "168"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    }
   },
   "nodoc": {
    "deepseek-r1:14b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       5
      ],
      "abstain": [
       9
      ],
      "hedged": [
       0
      ],
      "other": [
       153
      ],
      "unresolved": [
       1
      ],
      "answered": [
       153
      ]
     },
     "rates": {
      "correct": [
       0.02976190476190476
      ],
      "abstain": [
       0.05357142857142857
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9107142857142857
      ],
      "unresolved": [
       0.005952380952380952
      ],
      "answered": [
       0.9107142857142857
      ]
     },
     "disp": {
      "correct": {
       "p0": "3",
       "p1": "3.0",
       "count": "5"
      },
      "abstain": {
       "p0": "5",
       "p1": "5.4",
       "count": "9"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "91",
       "p1": "91.1",
       "count": "153"
      },
      "unresolved": {
       "p0": "1",
       "p1": "0.6",
       "count": "1"
      },
      "answered": {
       "p0": "91",
       "p1": "91.1",
       "count": "153"
      }
     }
    },
    "deepseek-r1:8b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       4
      ],
      "abstain": [
       49
      ],
      "hedged": [
       0
      ],
      "other": [
       104
      ],
      "unresolved": [
       11
      ],
      "answered": [
       104
      ]
     },
     "rates": {
      "correct": [
       0.023809523809523808
      ],
      "abstain": [
       0.2916666666666667
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.6190476190476191
      ],
      "unresolved": [
       0.06547619047619048
      ],
      "answered": [
       0.6190476190476191
      ]
     },
     "disp": {
      "correct": {
       "p0": "2",
       "p1": "2.4",
       "count": "4"
      },
      "abstain": {
       "p0": "29",
       "p1": "29.2",
       "count": "49"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "62",
       "p1": "61.9",
       "count": "104"
      },
      "unresolved": {
       "p0": "7",
       "p1": "6.5",
       "count": "11"
      },
      "answered": {
       "p0": "62",
       "p1": "61.9",
       "count": "104"
      }
     }
    },
    "gemma3:12b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       7
      ],
      "abstain": [
       2
      ],
      "hedged": [
       0
      ],
      "other": [
       159
      ],
      "unresolved": [
       0
      ],
      "answered": [
       159
      ]
     },
     "rates": {
      "correct": [
       0.041666666666666664
      ],
      "abstain": [
       0.011904761904761904
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9464285714285714
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.9464285714285714
      ]
     },
     "disp": {
      "correct": {
       "p0": "4",
       "p1": "4.2",
       "count": "7"
      },
      "abstain": {
       "p0": "1",
       "p1": "1.2",
       "count": "2"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "95",
       "p1": "94.6",
       "count": "159"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "95",
       "p1": "94.6",
       "count": "159"
      }
     }
    },
    "gemma3:27b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       8
      ],
      "abstain": [
       2
      ],
      "hedged": [
       0
      ],
      "other": [
       158
      ],
      "unresolved": [
       0
      ],
      "answered": [
       158
      ]
     },
     "rates": {
      "correct": [
       0.047619047619047616
      ],
      "abstain": [
       0.011904761904761904
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9404761904761905
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.9404761904761905
      ]
     },
     "disp": {
      "correct": {
       "p0": "5",
       "p1": "4.8",
       "count": "8"
      },
      "abstain": {
       "p0": "1",
       "p1": "1.2",
       "count": "2"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "94",
       "p1": "94.0",
       "count": "158"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "94",
       "p1": "94.0",
       "count": "158"
      }
     }
    },
    "gemma4:12b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       14
      ],
      "abstain": [
       62
      ],
      "hedged": [
       0
      ],
      "other": [
       92
      ],
      "unresolved": [
       0
      ],
      "answered": [
       92
      ]
     },
     "rates": {
      "correct": [
       0.08333333333333333
      ],
      "abstain": [
       0.36904761904761907
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.5476190476190477
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.5476190476190477
      ]
     },
     "disp": {
      "correct": {
       "p0": "8",
       "p1": "8.3",
       "count": "14"
      },
      "abstain": {
       "p0": "37",
       "p1": "36.9",
       "count": "62"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "55",
       "p1": "54.8",
       "count": "92"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "55",
       "p1": "54.8",
       "count": "92"
      }
     }
    },
    "gemma4:26b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       13
      ],
      "abstain": [
       50
      ],
      "hedged": [
       1
      ],
      "other": [
       104
      ],
      "unresolved": [
       0
      ],
      "answered": [
       105
      ]
     },
     "rates": {
      "correct": [
       0.07738095238095238
      ],
      "abstain": [
       0.2976190476190476
      ],
      "hedged": [
       0.005952380952380952
      ],
      "other": [
       0.6190476190476191
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.625
      ]
     },
     "disp": {
      "correct": {
       "p0": "8",
       "p1": "7.7",
       "count": "13"
      },
      "abstain": {
       "p0": "30",
       "p1": "29.8",
       "count": "50"
      },
      "hedged": {
       "p0": "1",
       "p1": "0.6",
       "count": "1"
      },
      "other": {
       "p0": "62",
       "p1": "61.9",
       "count": "104"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "63",
       "p1": "62.5",
       "count": "105"
      }
     }
    },
    "gpt-oss:120b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       10
      ],
      "abstain": [
       2
      ],
      "hedged": [
       0
      ],
      "other": [
       156
      ],
      "unresolved": [
       0
      ],
      "answered": [
       156
      ]
     },
     "rates": {
      "correct": [
       0.05952380952380952
      ],
      "abstain": [
       0.011904761904761904
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9285714285714286
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.9285714285714286
      ]
     },
     "disp": {
      "correct": {
       "p0": "6",
       "p1": "6.0",
       "count": "10"
      },
      "abstain": {
       "p0": "1",
       "p1": "1.2",
       "count": "2"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "93",
       "p1": "92.9",
       "count": "156"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "93",
       "p1": "92.9",
       "count": "156"
      }
     }
    },
    "gpt-oss:20b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       9
      ],
      "abstain": [
       0
      ],
      "hedged": [
       0
      ],
      "other": [
       158
      ],
      "unresolved": [
       1
      ],
      "answered": [
       158
      ]
     },
     "rates": {
      "correct": [
       0.05357142857142857
      ],
      "abstain": [
       0.0
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9404761904761905
      ],
      "unresolved": [
       0.005952380952380952
      ],
      "answered": [
       0.9404761904761905
      ]
     },
     "disp": {
      "correct": {
       "p0": "5",
       "p1": "5.4",
       "count": "9"
      },
      "abstain": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "94",
       "p1": "94.0",
       "count": "158"
      },
      "unresolved": {
       "p0": "1",
       "p1": "0.6",
       "count": "1"
      },
      "answered": {
       "p0": "94",
       "p1": "94.0",
       "count": "158"
      }
     }
    },
    "llama3.1:8b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       3
      ],
      "abstain": [
       2
      ],
      "hedged": [
       0
      ],
      "other": [
       163
      ],
      "unresolved": [
       0
      ],
      "answered": [
       163
      ]
     },
     "rates": {
      "correct": [
       0.017857142857142856
      ],
      "abstain": [
       0.011904761904761904
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9702380952380952
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.9702380952380952
      ]
     },
     "disp": {
      "correct": {
       "p0": "2",
       "p1": "1.8",
       "count": "3"
      },
      "abstain": {
       "p0": "1",
       "p1": "1.2",
       "count": "2"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "97",
       "p1": "97.0",
       "count": "163"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "97",
       "p1": "97.0",
       "count": "163"
      }
     }
    },
    "mistral-small3.2:24b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       8
      ],
      "abstain": [
       9
      ],
      "hedged": [
       0
      ],
      "other": [
       151
      ],
      "unresolved": [
       0
      ],
      "answered": [
       151
      ]
     },
     "rates": {
      "correct": [
       0.047619047619047616
      ],
      "abstain": [
       0.05357142857142857
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.8988095238095238
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.8988095238095238
      ]
     },
     "disp": {
      "correct": {
       "p0": "5",
       "p1": "4.8",
       "count": "8"
      },
      "abstain": {
       "p0": "5",
       "p1": "5.4",
       "count": "9"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "90",
       "p1": "89.9",
       "count": "151"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "90",
       "p1": "89.9",
       "count": "151"
      }
     }
    },
    "phi4:14b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       5
      ],
      "abstain": [
       40
      ],
      "hedged": [
       1
      ],
      "other": [
       121
      ],
      "unresolved": [
       1
      ],
      "answered": [
       122
      ]
     },
     "rates": {
      "correct": [
       0.02976190476190476
      ],
      "abstain": [
       0.23809523809523808
      ],
      "hedged": [
       0.005952380952380952
      ],
      "other": [
       0.7202380952380952
      ],
      "unresolved": [
       0.005952380952380952
      ],
      "answered": [
       0.7261904761904762
      ]
     },
     "disp": {
      "correct": {
       "p0": "3",
       "p1": "3.0",
       "count": "5"
      },
      "abstain": {
       "p0": "24",
       "p1": "23.8",
       "count": "40"
      },
      "hedged": {
       "p0": "1",
       "p1": "0.6",
       "count": "1"
      },
      "other": {
       "p0": "72",
       "p1": "72.0",
       "count": "121"
      },
      "unresolved": {
       "p0": "1",
       "p1": "0.6",
       "count": "1"
      },
      "answered": {
       "p0": "73",
       "p1": "72.6",
       "count": "122"
      }
     }
    },
    "qwen3.5:27b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       12
      ],
      "abstain": [
       24
      ],
      "hedged": [
       0
      ],
      "other": [
       132
      ],
      "unresolved": [
       0
      ],
      "answered": [
       132
      ]
     },
     "rates": {
      "correct": [
       0.07142857142857142
      ],
      "abstain": [
       0.14285714285714285
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.7857142857142857
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.7857142857142857
      ]
     },
     "disp": {
      "correct": {
       "p0": "7",
       "p1": "7.1",
       "count": "12"
      },
      "abstain": {
       "p0": "14",
       "p1": "14.3",
       "count": "24"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "79",
       "p1": "78.6",
       "count": "132"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "79",
       "p1": "78.6",
       "count": "132"
      }
     }
    },
    "qwen3.5:9b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       8
      ],
      "abstain": [
       25
      ],
      "hedged": [
       0
      ],
      "other": [
       135
      ],
      "unresolved": [
       0
      ],
      "answered": [
       135
      ]
     },
     "rates": {
      "correct": [
       0.047619047619047616
      ],
      "abstain": [
       0.1488095238095238
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.8035714285714286
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.8035714285714286
      ]
     },
     "disp": {
      "correct": {
       "p0": "5",
       "p1": "4.8",
       "count": "8"
      },
      "abstain": {
       "p0": "15",
       "p1": "14.9",
       "count": "25"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "80",
       "p1": "80.4",
       "count": "135"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "80",
       "p1": "80.4",
       "count": "135"
      }
     }
    },
    "qwen3:14b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       8
      ],
      "abstain": [
       1
      ],
      "hedged": [
       0
      ],
      "other": [
       158
      ],
      "unresolved": [
       1
      ],
      "answered": [
       158
      ]
     },
     "rates": {
      "correct": [
       0.047619047619047616
      ],
      "abstain": [
       0.005952380952380952
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9404761904761905
      ],
      "unresolved": [
       0.005952380952380952
      ],
      "answered": [
       0.9404761904761905
      ]
     },
     "disp": {
      "correct": {
       "p0": "5",
       "p1": "4.8",
       "count": "8"
      },
      "abstain": {
       "p0": "1",
       "p1": "0.6",
       "count": "1"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "94",
       "p1": "94.0",
       "count": "158"
      },
      "unresolved": {
       "p0": "1",
       "p1": "0.6",
       "count": "1"
      },
      "answered": {
       "p0": "94",
       "p1": "94.0",
       "count": "158"
      }
     }
    },
    "qwen3:30b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       7
      ],
      "abstain": [
       8
      ],
      "hedged": [
       0
      ],
      "other": [
       153
      ],
      "unresolved": [
       0
      ],
      "answered": [
       153
      ]
     },
     "rates": {
      "correct": [
       0.041666666666666664
      ],
      "abstain": [
       0.047619047619047616
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9107142857142857
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.9107142857142857
      ]
     },
     "disp": {
      "correct": {
       "p0": "4",
       "p1": "4.2",
       "count": "7"
      },
      "abstain": {
       "p0": "5",
       "p1": "4.8",
       "count": "8"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "91",
       "p1": "91.1",
       "count": "153"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "91",
       "p1": "91.1",
       "count": "153"
      }
     }
    },
    "qwen3:8b": {
     "runs": [
      1
     ],
     "n": [
      168
     ],
     "counts": {
      "correct": [
       9
      ],
      "abstain": [
       1
      ],
      "hedged": [
       0
      ],
      "other": [
       157
      ],
      "unresolved": [
       1
      ],
      "answered": [
       157
      ]
     },
     "rates": {
      "correct": [
       0.05357142857142857
      ],
      "abstain": [
       0.005952380952380952
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9345238095238095
      ],
      "unresolved": [
       0.005952380952380952
      ],
      "answered": [
       0.9345238095238095
      ]
     },
     "disp": {
      "correct": {
       "p0": "5",
       "p1": "5.4",
       "count": "9"
      },
      "abstain": {
       "p0": "1",
       "p1": "0.6",
       "count": "1"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "93",
       "p1": "93.5",
       "count": "157"
      },
      "unresolved": {
       "p0": "1",
       "p1": "0.6",
       "count": "1"
      },
      "answered": {
       "p0": "93",
       "p1": "93.5",
       "count": "157"
      }
     }
    }
   },
   "ranges_models": {
    "plain|answerable|answered": {
     "lo": 0.005952380952380952,
     "hi": 0.10119047619047619,
     "lo_model": "qwen3.5:27b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.005952380952380952,
     "mean_hi": 0.09821428571428571,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.03571428571428571,
     "n_models": 16,
     "disp": {
      "p0": "1〜10",
      "p1": "0.6〜10.1"
     }
    },
    "plain|answerable|abstain": {
     "lo": 0.0,
     "hi": 0.011904761904761904,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3.5:9b",
     "mean_lo": 0.0,
     "mean_hi": 0.011904761904761904,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3.5:9b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜1.2"
     }
    },
    "plain|answerable|correct": {
     "lo": 0.8154761904761905,
     "hi": 0.9940476190476191,
     "lo_model": "deepseek-r1:8b",
     "hi_model": "qwen3.5:27b",
     "mean_lo": 0.8273809523809523,
     "mean_hi": 0.9940476190476191,
     "mean_lo_model": "deepseek-r1:8b",
     "mean_hi_model": "qwen3.5:27b",
     "median_of_means": 0.9642857142857143,
     "n_models": 16,
     "disp": {
      "p0": "82〜99",
      "p1": "81.5〜99.4"
     }
    },
    "plain|answerable|other": {
     "lo": 0.005952380952380952,
     "hi": 0.10119047619047619,
     "lo_model": "qwen3.5:27b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.005952380952380952,
     "mean_hi": 0.09821428571428571,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.03571428571428571,
     "n_models": 16,
     "disp": {
      "p0": "1〜10",
      "p1": "0.6〜10.1"
     }
    },
    "plain|answerable|hedged": {
     "lo": 0.0,
     "hi": 0.0,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.0,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0",
      "p1": "0.0"
     }
    },
    "plain|answerable|unresolved": {
     "lo": 0.0,
     "hi": 0.07738095238095238,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.0625,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜8",
      "p1": "0.0〜7.7"
     }
    },
    "plain|near|answered": {
     "lo": 0.23214285714285715,
     "hi": 0.8333333333333334,
     "lo_model": "gemma4:26b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.23809523809523808,
     "mean_hi": 0.8244047619047619,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.5148809523809523,
     "n_models": 16,
     "disp": {
      "p0": "23〜83",
      "p1": "23.2〜83.3"
     }
    },
    "plain|near|abstain": {
     "lo": 0.11904761904761904,
     "hi": 0.7440476190476191,
     "lo_model": "qwen3:30b",
     "hi_model": "qwen3.5:27b",
     "mean_lo": 0.12797619047619047,
     "mean_hi": 0.7440476190476191,
     "mean_lo_model": "qwen3:30b",
     "mean_hi_model": "qwen3.5:27b",
     "median_of_means": 0.39285714285714285,
     "n_models": 16,
     "disp": {
      "p0": "12〜74",
      "p1": "11.9〜74.4"
     }
    },
    "plain|near|correct": {
     "lo": 0.011904761904761904,
     "hi": 0.07738095238095238,
     "lo_model": "gemma3:12b",
     "hi_model": "gpt-oss:120b",
     "mean_lo": 0.011904761904761904,
     "mean_hi": 0.06845238095238096,
     "mean_lo_model": "gemma3:12b",
     "mean_hi_model": "gpt-oss:120b",
     "median_of_means": 0.023809523809523808,
     "n_models": 16,
     "disp": {
      "p0": "1〜8",
      "p1": "1.2〜7.7"
     }
    },
    "plain|near|other": {
     "lo": 0.23214285714285715,
     "hi": 0.8333333333333334,
     "lo_model": "gemma4:26b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.23809523809523808,
     "mean_hi": 0.8244047619047619,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.5148809523809523,
     "n_models": 16,
     "disp": {
      "p0": "23〜83",
      "p1": "23.2〜83.3"
     }
    },
    "plain|near|hedged": {
     "lo": 0.0,
     "hi": 0.011904761904761904,
     "lo_model": "qwen3:8b",
     "hi_model": "phi4:14b",
     "mean_lo": 0.0,
     "mean_hi": 0.011904761904761904,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "phi4:14b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜1.2"
     }
    },
    "plain|near|unresolved": {
     "lo": 0.0,
     "hi": 0.2261904761904762,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:30b",
     "mean_lo": 0.0,
     "mean_hi": 0.20238095238095238,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3:30b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜23",
      "p1": "0.0〜22.6"
     }
    },
    "plain|far|answered": {
     "lo": 0.005952380952380952,
     "hi": 0.8333333333333334,
     "lo_model": "qwen3.5:27b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.008928571428571428,
     "mean_hi": 0.8303571428571429,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.10119047619047619,
     "n_models": 16,
     "disp": {
      "p0": "1〜83",
      "p1": "0.6〜83.3"
     }
    },
    "plain|far|abstain": {
     "lo": 0.1130952380952381,
     "hi": 0.9940476190476191,
     "lo_model": "gpt-oss:20b",
     "hi_model": "qwen3.5:27b",
     "mean_lo": 0.1130952380952381,
     "mean_hi": 0.9910714285714286,
     "mean_lo_model": "gpt-oss:20b",
     "mean_hi_model": "qwen3.5:27b",
     "median_of_means": 0.8854166666666666,
     "n_models": 16,
     "disp": {
      "p0": "11〜99",
      "p1": "11.3〜99.4"
     }
    },
    "plain|far|correct": {
     "lo": 0.0,
     "hi": 0.07142857142857142,
     "lo_model": "qwen3:8b",
     "hi_model": "gpt-oss:120b",
     "mean_lo": 0.0,
     "mean_hi": 0.06547619047619048,
     "mean_lo_model": "qwen3:14b",
     "mean_hi_model": "gpt-oss:120b",
     "median_of_means": 0.001488095238095238,
     "n_models": 16,
     "disp": {
      "p0": "0〜7",
      "p1": "0.0〜7.1"
     }
    },
    "plain|far|other": {
     "lo": 0.005952380952380952,
     "hi": 0.8333333333333334,
     "lo_model": "qwen3.5:27b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.008928571428571428,
     "mean_hi": 0.8303571428571429,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.09970238095238096,
     "n_models": 16,
     "disp": {
      "p0": "1〜83",
      "p1": "0.6〜83.3"
     }
    },
    "plain|far|hedged": {
     "lo": 0.0,
     "hi": 0.005952380952380952,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.002976190476190476,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜0.6"
     }
    },
    "plain|far|unresolved": {
     "lo": 0.0,
     "hi": 0.1130952380952381,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.10416666666666667,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜11",
      "p1": "0.0〜11.3"
     }
    },
    "abstain|answerable|answered": {
     "lo": 0.005952380952380952,
     "hi": 0.08928571428571429,
     "lo_model": "qwen3.5:9b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.005952380952380952,
     "mean_hi": 0.08630952380952381,
     "mean_lo_model": "qwen3.5:9b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.025297619047619048,
     "n_models": 16,
     "disp": {
      "p0": "1〜9",
      "p1": "0.6〜8.9"
     }
    },
    "abstain|answerable|abstain": {
     "lo": 0.0,
     "hi": 0.11904761904761904,
     "lo_model": "gpt-oss:20b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.002976190476190476,
     "mean_hi": 0.09821428571428571,
     "mean_lo_model": "gpt-oss:20b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.023809523809523808,
     "n_models": 16,
     "disp": {
      "p0": "0〜12",
      "p1": "0.0〜11.9"
     }
    },
    "abstain|answerable|correct": {
     "lo": 0.7619047619047619,
     "hi": 0.9761904761904762,
     "lo_model": "deepseek-r1:8b",
     "hi_model": "qwen3.5:27b",
     "mean_lo": 0.7857142857142857,
     "mean_hi": 0.9732142857142857,
     "mean_lo_model": "deepseek-r1:8b",
     "mean_hi_model": "qwen3.5:27b",
     "median_of_means": 0.9494047619047619,
     "n_models": 16,
     "disp": {
      "p0": "76〜98",
      "p1": "76.2〜97.6"
     }
    },
    "abstain|answerable|other": {
     "lo": 0.005952380952380952,
     "hi": 0.08928571428571429,
     "lo_model": "qwen3.5:9b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.005952380952380952,
     "mean_hi": 0.08630952380952381,
     "mean_lo_model": "qwen3.5:9b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.023809523809523808,
     "n_models": 16,
     "disp": {
      "p0": "1〜9",
      "p1": "0.6〜8.9"
     }
    },
    "abstain|answerable|hedged": {
     "lo": 0.0,
     "hi": 0.005952380952380952,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.005952380952380952,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "phi4:14b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜0.6"
     }
    },
    "abstain|answerable|unresolved": {
     "lo": 0.0,
     "hi": 0.05357142857142857,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.044642857142857144,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜5",
      "p1": "0.0〜5.4"
     }
    },
    "abstain|near|answered": {
     "lo": 0.041666666666666664,
     "hi": 0.27380952380952384,
     "lo_model": "qwen3.5:27b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.041666666666666664,
     "mean_hi": 0.27380952380952384,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.15625,
     "n_models": 16,
     "disp": {
      "p0": "4〜27",
      "p1": "4.2〜27.4"
     }
    },
    "abstain|near|abstain": {
     "lo": 0.6904761904761905,
     "hi": 0.9464285714285714,
     "lo_model": "gpt-oss:20b",
     "hi_model": "qwen3.5:27b",
     "mean_lo": 0.6904761904761905,
     "mean_hi": 0.9464285714285714,
     "mean_lo_model": "gpt-oss:20b",
     "mean_hi_model": "qwen3.5:27b",
     "median_of_means": 0.8154761904761905,
     "n_models": 16,
     "disp": {
      "p0": "69〜95",
      "p1": "69.0〜94.6"
     }
    },
    "abstain|near|correct": {
     "lo": 0.005952380952380952,
     "hi": 0.041666666666666664,
     "lo_model": "gemma4:12b",
     "hi_model": "qwen3:30b",
     "mean_lo": 0.005952380952380952,
     "mean_hi": 0.03869047619047619,
     "mean_lo_model": "gemma4:12b",
     "mean_hi_model": "qwen3:30b",
     "median_of_means": 0.017857142857142856,
     "n_models": 16,
     "disp": {
      "p0": "1〜4",
      "p1": "0.6〜4.2"
     }
    },
    "abstain|near|other": {
     "lo": 0.041666666666666664,
     "hi": 0.27380952380952384,
     "lo_model": "qwen3.5:27b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.041666666666666664,
     "mean_hi": 0.27380952380952384,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.15625,
     "n_models": 16,
     "disp": {
      "p0": "4〜27",
      "p1": "4.2〜27.4"
     }
    },
    "abstain|near|hedged": {
     "lo": 0.0,
     "hi": 0.005952380952380952,
     "lo_model": "qwen3:14b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.005952380952380952,
     "mean_lo_model": "qwen3:14b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜0.6"
     }
    },
    "abstain|near|unresolved": {
     "lo": 0.0,
     "hi": 0.13095238095238096,
     "lo_model": "qwen3:8b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.125,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜13",
      "p1": "0.0〜13.1"
     }
    },
    "abstain|far|answered": {
     "lo": 0.0,
     "hi": 0.03571428571428571,
     "lo_model": "qwen3:14b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.0,
     "mean_hi": 0.03273809523809524,
     "mean_lo_model": "qwen3:14b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜4",
      "p1": "0.0〜3.6"
     }
    },
    "abstain|far|abstain": {
     "lo": 0.9583333333333334,
     "hi": 1.0,
     "lo_model": "gpt-oss:20b",
     "hi_model": "qwen3:14b",
     "mean_lo": 0.9613095238095238,
     "mean_hi": 1.0,
     "mean_lo_model": "gpt-oss:20b",
     "mean_hi_model": "qwen3:14b",
     "median_of_means": 1.0,
     "n_models": 16,
     "disp": {
      "p0": "96〜100",
      "p1": "95.8〜100.0"
     }
    },
    "abstain|far|correct": {
     "lo": 0.0,
     "hi": 0.005952380952380952,
     "lo_model": "qwen3:8b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.0,
     "mean_hi": 0.005952380952380952,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜0.6"
     }
    },
    "abstain|far|other": {
     "lo": 0.0,
     "hi": 0.03571428571428571,
     "lo_model": "qwen3:14b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.0,
     "mean_hi": 0.03273809523809524,
     "mean_lo_model": "qwen3:14b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜4",
      "p1": "0.0〜3.6"
     }
    },
    "abstain|far|hedged": {
     "lo": 0.0,
     "hi": 0.0,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.0,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0",
      "p1": "0.0"
     }
    },
    "abstain|far|unresolved": {
     "lo": 0.0,
     "hi": 0.017857142857142856,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.01488095238095238,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜2",
      "p1": "0.0〜1.8"
     }
    },
    "quote|answerable|answered": {
     "lo": 0.0,
     "hi": 0.1130952380952381,
     "lo_model": "gemma4:12b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.11011904761904762,
     "mean_lo_model": "gemma4:12b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.023809523809523808,
     "n_models": 16,
     "disp": {
      "p0": "0〜11",
      "p1": "0.0〜11.3"
     }
    },
    "quote|answerable|abstain": {
     "lo": 0.005952380952380952,
     "hi": 0.34523809523809523,
     "lo_model": "qwen3:30b",
     "hi_model": "qwen3.5:9b",
     "mean_lo": 0.005952380952380952,
     "mean_hi": 0.34523809523809523,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "qwen3.5:9b",
     "median_of_means": 0.011904761904761904,
     "n_models": 16,
     "disp": {
      "p0": "1〜35",
      "p1": "0.6〜34.5"
     }
    },
    "quote|answerable|correct": {
     "lo": 0.6369047619047619,
     "hi": 0.9940476190476191,
     "lo_model": "qwen3.5:9b",
     "hi_model": "gpt-oss:120b",
     "mean_lo": 0.6369047619047619,
     "mean_hi": 0.9910714285714286,
     "mean_lo_model": "qwen3.5:9b",
     "mean_hi_model": "gpt-oss:120b",
     "median_of_means": 0.9627976190476191,
     "n_models": 16,
     "disp": {
      "p0": "64〜99",
      "p1": "63.7〜99.4"
     }
    },
    "quote|answerable|other": {
     "lo": 0.0,
     "hi": 0.1130952380952381,
     "lo_model": "gemma4:12b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.11011904761904762,
     "mean_lo_model": "gemma4:12b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.023809523809523808,
     "n_models": 16,
     "disp": {
      "p0": "0〜11",
      "p1": "0.0〜11.3"
     }
    },
    "quote|answerable|hedged": {
     "lo": 0.0,
     "hi": 0.005952380952380952,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:14b",
     "mean_lo": 0.0,
     "mean_hi": 0.002976190476190476,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "deepseek-r1:14b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜0.6"
     }
    },
    "quote|answerable|unresolved": {
     "lo": 0.0,
     "hi": 0.05357142857142857,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.041666666666666664,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜5",
      "p1": "0.0〜5.4"
     }
    },
    "quote|near|answered": {
     "lo": 0.041666666666666664,
     "hi": 0.6369047619047619,
     "lo_model": "qwen3.5:9b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.041666666666666664,
     "mean_hi": 0.6220238095238095,
     "mean_lo_model": "qwen3.5:9b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.14285714285714285,
     "n_models": 16,
     "disp": {
      "p0": "4〜64",
      "p1": "4.2〜63.7"
     }
    },
    "quote|near|abstain": {
     "lo": 0.32142857142857145,
     "hi": 0.9523809523809523,
     "lo_model": "llama3.1:8b",
     "hi_model": "qwen3.5:9b",
     "mean_lo": 0.3273809523809524,
     "mean_hi": 0.9523809523809523,
     "mean_lo_model": "llama3.1:8b",
     "mean_hi_model": "qwen3.5:9b",
     "median_of_means": 0.8125,
     "n_models": 16,
     "disp": {
      "p0": "32〜95",
      "p1": "32.1〜95.2"
     }
    },
    "quote|near|correct": {
     "lo": 0.005952380952380952,
     "hi": 0.041666666666666664,
     "lo_model": "qwen3.5:9b",
     "hi_model": "qwen3:30b",
     "mean_lo": 0.005952380952380952,
     "mean_hi": 0.03571428571428571,
     "mean_lo_model": "qwen3.5:9b",
     "mean_hi_model": "qwen3:30b",
     "median_of_means": 0.022321428571428572,
     "n_models": 16,
     "disp": {
      "p0": "1〜4",
      "p1": "0.6〜4.2"
     }
    },
    "quote|near|other": {
     "lo": 0.041666666666666664,
     "hi": 0.6369047619047619,
     "lo_model": "qwen3.5:9b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.041666666666666664,
     "mean_hi": 0.6220238095238095,
     "mean_lo_model": "qwen3.5:9b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.14136904761904762,
     "n_models": 16,
     "disp": {
      "p0": "4〜64",
      "p1": "4.2〜63.7"
     }
    },
    "quote|near|hedged": {
     "lo": 0.0,
     "hi": 0.005952380952380952,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.002976190476190476,
     "mean_lo_model": "qwen3:14b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜0.6"
     }
    },
    "quote|near|unresolved": {
     "lo": 0.0,
     "hi": 0.1130952380952381,
     "lo_model": "qwen3:14b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.10416666666666667,
     "mean_lo_model": "qwen3:14b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.001488095238095238,
     "n_models": 16,
     "disp": {
      "p0": "0〜11",
      "p1": "0.0〜11.3"
     }
    },
    "quote|far|answered": {
     "lo": 0.0,
     "hi": 0.2857142857142857,
     "lo_model": "qwen3:8b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.27380952380952384,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.001488095238095238,
     "n_models": 16,
     "disp": {
      "p0": "0〜29",
      "p1": "0.0〜28.6"
     }
    },
    "quote|far|abstain": {
     "lo": 0.6964285714285714,
     "hi": 1.0,
     "lo_model": "llama3.1:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.7083333333333334,
     "mean_hi": 1.0,
     "mean_lo_model": "llama3.1:8b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.9985119047619048,
     "n_models": 16,
     "disp": {
      "p0": "70〜100",
      "p1": "69.6〜100.0"
     }
    },
    "quote|far|correct": {
     "lo": 0.0,
     "hi": 0.0,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.0,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0",
      "p1": "0.0"
     }
    },
    "quote|far|other": {
     "lo": 0.0,
     "hi": 0.2857142857142857,
     "lo_model": "qwen3:8b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.27380952380952384,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.001488095238095238,
     "n_models": 16,
     "disp": {
      "p0": "0〜29",
      "p1": "0.0〜28.6"
     }
    },
    "quote|far|hedged": {
     "lo": 0.0,
     "hi": 0.0,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.0,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0",
      "p1": "0.0"
     }
    },
    "quote|far|unresolved": {
     "lo": 0.0,
     "hi": 0.023809523809523808,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.017857142857142856,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜2",
      "p1": "0.0〜2.4"
     }
    }
   },
   "tests": {
    "near_answered": {
     "title": "近い話題で答えを出した（答えを出した＋断りながら答えた）",
     "condition": "near",
     "finals": [
      "other",
      "hedged"
     ],
     "models": {
      "qwen3:8b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 58,
         "plain_only": 109,
         "abstain_only": 1,
         "p": 1.7102257906158654e-31,
         "p_holm": 2.565338685923798e-30,
         "plain_rate": 0.8333333333333334,
         "abstain_rate": 0.19047619047619047
        },
        {
         "n_pairs": 168,
         "n_ties": 61,
         "plain_only": 106,
         "abstain_only": 1,
         "p": 1.3312027775604574e-30,
         "p_holm": 1.8636838885846404e-29,
         "plain_rate": 0.8154761904761905,
         "abstain_rate": 0.19047619047619047
        }
       ],
       "p_holm_max": 1.8636838885846404e-29,
       "significant_both": true,
       "plain_greater_both": true
      },
      "qwen3:14b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 80,
         "plain_only": 88,
         "abstain_only": 0,
         "p": 6.462348535570529e-27,
         "p_holm": 8.401053096241687e-26,
         "plain_rate": 0.6904761904761905,
         "abstain_rate": 0.16666666666666666
        },
        {
         "n_pairs": 168,
         "n_ties": 75,
         "plain_only": 93,
         "abstain_only": 0,
         "p": 2.0194839173657902e-28,
         "p_holm": 2.6253290925755273e-27,
         "plain_rate": 0.7202380952380952,
         "abstain_rate": 0.16666666666666666
        }
       ],
       "p_holm_max": 8.401053096241687e-26,
       "significant_both": true,
       "plain_greater_both": true
      },
      "qwen3:30b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 92,
         "plain_only": 74,
         "abstain_only": 2,
         "p": 7.747704489416678e-20,
         "p_holm": 7.747704489416678e-19,
         "plain_rate": 0.6369047619047619,
         "abstain_rate": 0.20833333333333334
        },
        {
         "n_pairs": 168,
         "n_ties": 97,
         "plain_only": 68,
         "abstain_only": 3,
         "p": 5.057803134644878e-17,
         "p_holm": 4.55202282118039e-16,
         "plain_rate": 0.6011904761904762,
         "abstain_rate": 0.21428571428571427
        }
       ],
       "p_holm_max": 4.55202282118039e-16,
       "significant_both": true,
       "plain_greater_both": true
      },
      "qwen3.5:9b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 119,
         "plain_only": 48,
         "abstain_only": 1,
         "p": 1.7763568394002505e-13,
         "p_holm": 1.0658141036401503e-12,
         "plain_rate": 0.39285714285714285,
         "abstain_rate": 0.1130952380952381
        },
        {
         "n_pairs": 168,
         "n_ties": 119,
         "plain_only": 49,
         "abstain_only": 0,
         "p": 3.552713678800501e-15,
         "p_holm": 2.4868995751603507e-14,
         "plain_rate": 0.39880952380952384,
         "abstain_rate": 0.10714285714285714
        }
       ],
       "p_holm_max": 1.0658141036401503e-12,
       "significant_both": true,
       "plain_greater_both": true
      },
      "qwen3.5:27b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 135,
         "plain_only": 33,
         "abstain_only": 0,
         "p": 2.3283064365386963e-10,
         "p_holm": 6.984919309616089e-10,
         "plain_rate": 0.23809523809523808,
         "abstain_rate": 0.041666666666666664
        },
        {
         "n_pairs": 168,
         "n_ties": 135,
         "plain_only": 33,
         "abstain_only": 0,
         "p": 2.3283064365386963e-10,
         "p_holm": 9.313225746154785e-10,
         "plain_rate": 0.23809523809523808,
         "abstain_rate": 0.041666666666666664
        }
       ],
       "p_holm_max": 9.313225746154785e-10,
       "significant_both": true,
       "plain_greater_both": true
      },
      "gemma3:12b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 126,
         "plain_only": 41,
         "abstain_only": 1,
         "p": 1.9554136088117957e-11,
         "p_holm": 9.777068044058979e-11,
         "plain_rate": 0.4107142857142857,
         "abstain_rate": 0.17261904761904762
        },
        {
         "n_pairs": 168,
         "n_ties": 127,
         "plain_only": 39,
         "abstain_only": 2,
         "p": 7.839844329282641e-10,
         "p_holm": 2.301575482283047e-09,
         "plain_rate": 0.39880952380952384,
         "abstain_rate": 0.17857142857142858
        }
       ],
       "p_holm_max": 2.301575482283047e-09,
       "significant_both": true,
       "plain_greater_both": true
      },
      "gemma3:27b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 120,
         "plain_only": 48,
         "abstain_only": 0,
         "p": 7.105427357601002e-15,
         "p_holm": 4.973799150320701e-14,
         "plain_rate": 0.49404761904761907,
         "abstain_rate": 0.20833333333333334
        },
        {
         "n_pairs": 168,
         "n_ties": 120,
         "plain_only": 47,
         "abstain_only": 1,
         "p": 3.481659405224491e-13,
         "p_holm": 2.0889956431346945e-12,
         "plain_rate": 0.48214285714285715,
         "abstain_rate": 0.20833333333333334
        }
       ],
       "p_holm_max": 2.0889956431346945e-12,
       "significant_both": true,
       "plain_greater_both": true
      },
      "gemma4:12b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 127,
         "plain_only": 40,
         "abstain_only": 1,
         "p": 3.8198777474462986e-11,
         "p_holm": 1.5279510989785194e-10,
         "plain_rate": 0.35119047619047616,
         "abstain_rate": 0.11904761904761904
        },
        {
         "n_pairs": 168,
         "n_ties": 128,
         "plain_only": 39,
         "abstain_only": 1,
         "p": 7.457856554538012e-11,
         "p_holm": 3.728928277269006e-10,
         "plain_rate": 0.35119047619047616,
         "abstain_rate": 0.125
        }
       ],
       "p_holm_max": 3.728928277269006e-10,
       "significant_both": true,
       "plain_greater_both": true
      },
      "gemma4:26b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 145,
         "plain_only": 23,
         "abstain_only": 0,
         "p": 2.384185791015625e-07,
         "p_holm": 2.384185791015625e-07,
         "plain_rate": 0.25,
         "abstain_rate": 0.1130952380952381
        },
        {
         "n_pairs": 168,
         "n_ties": 149,
         "plain_only": 19,
         "abstain_only": 0,
         "p": 3.814697265625e-06,
         "p_holm": 3.814697265625e-06,
         "plain_rate": 0.23214285714285715,
         "abstain_rate": 0.11904761904761904
        }
       ],
       "p_holm_max": 3.814697265625e-06,
       "significant_both": true,
       "plain_greater_both": true
      },
      "gpt-oss:20b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 80,
         "plain_only": 88,
         "abstain_only": 0,
         "p": 6.462348535570529e-27,
         "p_holm": 8.401053096241687e-26,
         "plain_rate": 0.7976190476190477,
         "abstain_rate": 0.27380952380952384
        },
        {
         "n_pairs": 168,
         "n_ties": 74,
         "plain_only": 93,
         "abstain_only": 1,
         "p": 9.592548607487504e-27,
         "p_holm": 1.1511058328985004e-25,
         "plain_rate": 0.8214285714285714,
         "abstain_rate": 0.27380952380952384
        }
       ],
       "p_holm_max": 1.1511058328985004e-25,
       "significant_both": true,
       "plain_greater_both": true
      },
      "gpt-oss:120b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 59,
         "plain_only": 107,
         "abstain_only": 2,
         "p": 1.8476601514473386e-29,
         "p_holm": 2.586724212026274e-28,
         "plain_rate": 0.7142857142857143,
         "abstain_rate": 0.08928571428571429
        },
        {
         "n_pairs": 168,
         "n_ties": 59,
         "plain_only": 108,
         "abstain_only": 1,
         "p": 3.389636702121535e-31,
         "p_holm": 5.084455053182303e-30,
         "plain_rate": 0.7321428571428571,
         "abstain_rate": 0.09523809523809523
        }
       ],
       "p_holm_max": 2.586724212026274e-28,
       "significant_both": true,
       "plain_greater_both": true
      },
      "deepseek-r1:8b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 106,
         "plain_only": 54,
         "abstain_only": 8,
         "p": 1.709326186236787e-09,
         "p_holm": 3.418652372473574e-09,
         "plain_rate": 0.4226190476190476,
         "abstain_rate": 0.1488095238095238
        },
        {
         "n_pairs": 168,
         "n_ties": 108,
         "plain_only": 53,
         "abstain_only": 7,
         "p": 7.671918274276823e-10,
         "p_holm": 2.301575482283047e-09,
         "plain_rate": 0.4107142857142857,
         "abstain_rate": 0.13690476190476192
        }
       ],
       "p_holm_max": 3.418652372473574e-09,
       "significant_both": true,
       "plain_greater_both": true
      },
      "deepseek-r1:14b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 95,
         "plain_only": 70,
         "abstain_only": 3,
         "p": 1.3742686052727396e-17,
         "p_holm": 1.2368417447454656e-16,
         "plain_rate": 0.5476190476190477,
         "abstain_rate": 0.1488095238095238
        },
        {
         "n_pairs": 168,
         "n_ties": 99,
         "plain_only": 67,
         "abstain_only": 2,
         "p": 8.185726402265558e-18,
         "p_holm": 8.185726402265558e-17,
         "plain_rate": 0.5357142857142857,
         "abstain_rate": 0.1488095238095238
        }
       ],
       "p_holm_max": 1.2368417447454656e-16,
       "significant_both": true,
       "plain_greater_both": true
      },
      "llama3.1:8b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 61,
         "plain_only": 107,
         "abstain_only": 0,
         "p": 1.232595164407831e-32,
         "p_holm": 1.9721522630525295e-31,
         "plain_rate": 0.8035714285714286,
         "abstain_rate": 0.16666666666666666
        },
        {
         "n_pairs": 168,
         "n_ties": 60,
         "plain_only": 108,
         "abstain_only": 0,
         "p": 6.162975822039155e-33,
         "p_holm": 9.860761315262648e-32,
         "plain_rate": 0.8035714285714286,
         "abstain_rate": 0.16071428571428573
        }
       ],
       "p_holm_max": 1.9721522630525295e-31,
       "significant_both": true,
       "plain_greater_both": true
      },
      "mistral-small3.2:24b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 96,
         "plain_only": 72,
         "abstain_only": 0,
         "p": 4.235164736271502e-22,
         "p_holm": 4.658681209898652e-21,
         "plain_rate": 0.5952380952380952,
         "abstain_rate": 0.16666666666666666
        },
        {
         "n_pairs": 168,
         "n_ties": 94,
         "plain_only": 74,
         "abstain_only": 0,
         "p": 1.0587911840678754e-22,
         "p_holm": 1.164670302474663e-21,
         "plain_rate": 0.6071428571428571,
         "abstain_rate": 0.16666666666666666
        }
       ],
       "p_holm_max": 4.658681209898652e-21,
       "significant_both": true,
       "plain_greater_both": true
      },
      "phi4:14b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 110,
         "plain_only": 57,
         "abstain_only": 1,
         "p": 4.0939474033052647e-16,
         "p_holm": 3.2751579226442118e-15,
         "plain_rate": 0.40476190476190477,
         "abstain_rate": 0.07142857142857142
        },
        {
         "n_pairs": 168,
         "n_ties": 112,
         "plain_only": 55,
         "abstain_only": 1,
         "p": 1.582067810090848e-15,
         "p_holm": 1.2656542480726785e-14,
         "plain_rate": 0.39285714285714285,
         "abstain_rate": 0.07142857142857142
        }
       ],
       "p_holm_max": 1.2656542480726785e-14,
       "significant_both": true,
       "plain_greater_both": true
      }
     },
     "n_significant_both": 16
    },
    "answerable_correct": {
     "title": "答えありで正答",
     "condition": "answerable",
     "finals": [
      "correct"
     ],
     "models": {
      "qwen3:8b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 164,
         "plain_only": 4,
         "abstain_only": 0,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.9345238095238095,
         "abstain_rate": 0.9107142857142857
        },
        {
         "n_pairs": 168,
         "n_ties": 163,
         "plain_only": 4,
         "abstain_only": 1,
         "p": 0.375,
         "p_holm": 1.0,
         "plain_rate": 0.9285714285714286,
         "abstain_rate": 0.9107142857142857
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "qwen3:14b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 165,
         "plain_only": 2,
         "abstain_only": 1,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9761904761904762,
         "abstain_rate": 0.9702380952380952
        },
        {
         "n_pairs": 168,
         "n_ties": 165,
         "plain_only": 2,
         "abstain_only": 1,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9702380952380952,
         "abstain_rate": 0.9642857142857143
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "qwen3:30b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 162,
         "plain_only": 1,
         "abstain_only": 5,
         "p": 0.21875,
         "p_holm": 1.0,
         "plain_rate": 0.9226190476190477,
         "abstain_rate": 0.9464285714285714
        },
        {
         "n_pairs": 168,
         "n_ties": 162,
         "plain_only": 3,
         "abstain_only": 3,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9285714285714286,
         "abstain_rate": 0.9285714285714286
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "qwen3.5:9b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 159,
         "plain_only": 6,
         "abstain_only": 3,
         "p": 0.5078125,
         "p_holm": 1.0,
         "plain_rate": 0.9642857142857143,
         "abstain_rate": 0.9464285714285714
        },
        {
         "n_pairs": 168,
         "n_ties": 160,
         "plain_only": 6,
         "abstain_only": 2,
         "p": 0.2890625,
         "p_holm": 1.0,
         "plain_rate": 0.9702380952380952,
         "abstain_rate": 0.9464285714285714
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "qwen3.5:27b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 165,
         "plain_only": 3,
         "abstain_only": 0,
         "p": 0.25,
         "p_holm": 1.0,
         "plain_rate": 0.9940476190476191,
         "abstain_rate": 0.9761904761904762
        },
        {
         "n_pairs": 168,
         "n_ties": 164,
         "plain_only": 4,
         "abstain_only": 0,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.9940476190476191,
         "abstain_rate": 0.9702380952380952
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "gemma3:12b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 162,
         "plain_only": 5,
         "abstain_only": 1,
         "p": 0.21875,
         "p_holm": 1.0,
         "plain_rate": 0.9583333333333334,
         "abstain_rate": 0.9345238095238095
        },
        {
         "n_pairs": 168,
         "n_ties": 163,
         "plain_only": 4,
         "abstain_only": 1,
         "p": 0.375,
         "p_holm": 1.0,
         "plain_rate": 0.9583333333333334,
         "abstain_rate": 0.9404761904761905
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "gemma3:27b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 163,
         "plain_only": 2,
         "abstain_only": 3,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9583333333333334,
         "abstain_rate": 0.9642857142857143
        },
        {
         "n_pairs": 168,
         "n_ties": 163,
         "plain_only": 2,
         "abstain_only": 3,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9583333333333334,
         "abstain_rate": 0.9642857142857143
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gemma4:12b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 162,
         "plain_only": 5,
         "abstain_only": 1,
         "p": 0.21875,
         "p_holm": 1.0,
         "plain_rate": 0.9761904761904762,
         "abstain_rate": 0.9523809523809523
        },
        {
         "n_pairs": 168,
         "n_ties": 163,
         "plain_only": 4,
         "abstain_only": 1,
         "p": 0.375,
         "p_holm": 1.0,
         "plain_rate": 0.9761904761904762,
         "abstain_rate": 0.9583333333333334
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "gemma4:26b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 166,
         "plain_only": 2,
         "abstain_only": 0,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.9821428571428571,
         "abstain_rate": 0.9702380952380952
        },
        {
         "n_pairs": 168,
         "n_ties": 165,
         "plain_only": 3,
         "abstain_only": 0,
         "p": 0.25,
         "p_holm": 1.0,
         "plain_rate": 0.9821428571428571,
         "abstain_rate": 0.9642857142857143
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "gpt-oss:20b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 165,
         "plain_only": 2,
         "abstain_only": 1,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9702380952380952,
         "abstain_rate": 0.9642857142857143
        },
        {
         "n_pairs": 168,
         "n_ties": 165,
         "plain_only": 2,
         "abstain_only": 1,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9702380952380952,
         "abstain_rate": 0.9642857142857143
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "gpt-oss:120b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 161,
         "plain_only": 4,
         "abstain_only": 3,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9821428571428571,
         "abstain_rate": 0.9761904761904762
        },
        {
         "n_pairs": 168,
         "n_ties": 160,
         "plain_only": 4,
         "abstain_only": 4,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9702380952380952,
         "abstain_rate": 0.9702380952380952
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "deepseek-r1:8b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 131,
         "plain_only": 19,
         "abstain_only": 18,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.8154761904761905,
         "abstain_rate": 0.8095238095238095
        },
        {
         "n_pairs": 168,
         "n_ties": 127,
         "plain_only": 27,
         "abstain_only": 14,
         "p": 0.05958388801809633,
         "p_holm": 0.8341744322533486,
         "plain_rate": 0.8392857142857143,
         "abstain_rate": 0.7619047619047619
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "deepseek-r1:14b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 162,
         "plain_only": 4,
         "abstain_only": 2,
         "p": 0.6875,
         "p_holm": 1.0,
         "plain_rate": 0.9464285714285714,
         "abstain_rate": 0.9345238095238095
        },
        {
         "n_pairs": 168,
         "n_ties": 158,
         "plain_only": 4,
         "abstain_only": 6,
         "p": 0.75390625,
         "p_holm": 1.0,
         "plain_rate": 0.9285714285714286,
         "abstain_rate": 0.9404761904761905
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "llama3.1:8b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 149,
         "plain_only": 19,
         "abstain_only": 0,
         "p": 3.814697265625e-06,
         "p_holm": 6.103515625e-05,
         "plain_rate": 0.9464285714285714,
         "abstain_rate": 0.8333333333333334
        },
        {
         "n_pairs": 168,
         "n_ties": 147,
         "plain_only": 21,
         "abstain_only": 0,
         "p": 9.5367431640625e-07,
         "p_holm": 1.52587890625e-05,
         "plain_rate": 0.9523809523809523,
         "abstain_rate": 0.8273809523809523
        }
       ],
       "p_holm_max": 6.103515625e-05,
       "significant_both": true,
       "plain_greater_both": true
      },
      "mistral-small3.2:24b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 162,
         "plain_only": 4,
         "abstain_only": 2,
         "p": 0.6875,
         "p_holm": 1.0,
         "plain_rate": 0.9642857142857143,
         "abstain_rate": 0.9523809523809523
        },
        {
         "n_pairs": 168,
         "n_ties": 162,
         "plain_only": 4,
         "abstain_only": 2,
         "p": 0.6875,
         "p_holm": 1.0,
         "plain_rate": 0.9642857142857143,
         "abstain_rate": 0.9523809523809523
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "phi4:14b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 154,
         "plain_only": 14,
         "abstain_only": 0,
         "p": 0.0001220703125,
         "p_holm": 0.0018310546875,
         "plain_rate": 0.9642857142857143,
         "abstain_rate": 0.8809523809523809
        },
        {
         "n_pairs": 168,
         "n_ties": 153,
         "plain_only": 15,
         "abstain_only": 0,
         "p": 6.103515625e-05,
         "p_holm": 0.00091552734375,
         "plain_rate": 0.9642857142857143,
         "abstain_rate": 0.875
        }
       ],
       "p_holm_max": 0.0018310546875,
       "significant_both": true,
       "plain_greater_both": true
      }
     },
     "n_significant_both": 2
    },
    "answerable_abstain": {
     "title": "答えありで不要な辞退",
     "condition": "answerable",
     "finals": [
      "abstain"
     ],
     "models": {
      "qwen3:8b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 164,
         "plain_only": 0,
         "abstain_only": 4,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.023809523809523808
        },
        {
         "n_pairs": 168,
         "n_ties": 164,
         "plain_only": 0,
         "abstain_only": 4,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.023809523809523808
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "qwen3:14b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 166,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.011904761904761904
        },
        {
         "n_pairs": 168,
         "n_ties": 166,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.011904761904761904
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "qwen3:30b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 166,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.011904761904761904
        },
        {
         "n_pairs": 168,
         "n_ties": 167,
         "plain_only": 0,
         "abstain_only": 1,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.005952380952380952
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "qwen3.5:9b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 162,
         "plain_only": 0,
         "abstain_only": 6,
         "p": 0.03125,
         "p_holm": 0.40625,
         "plain_rate": 0.011904761904761904,
         "abstain_rate": 0.047619047619047616
        },
        {
         "n_pairs": 168,
         "n_ties": 162,
         "plain_only": 0,
         "abstain_only": 6,
         "p": 0.03125,
         "p_holm": 0.40625,
         "plain_rate": 0.011904761904761904,
         "abstain_rate": 0.047619047619047616
        }
       ],
       "p_holm_max": 0.40625,
       "significant_both": false,
       "plain_greater_both": false
      },
      "qwen3.5:27b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 165,
         "plain_only": 0,
         "abstain_only": 3,
         "p": 0.25,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.017857142857142856
        },
        {
         "n_pairs": 168,
         "n_ties": 164,
         "plain_only": 0,
         "abstain_only": 4,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.023809523809523808
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gemma3:12b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 164,
         "plain_only": 0,
         "abstain_only": 4,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.023809523809523808
        },
        {
         "n_pairs": 168,
         "n_ties": 164,
         "plain_only": 0,
         "abstain_only": 4,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.023809523809523808
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gemma3:27b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 166,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.011904761904761904
        },
        {
         "n_pairs": 168,
         "n_ties": 166,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.011904761904761904
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gemma4:12b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 163,
         "plain_only": 0,
         "abstain_only": 5,
         "p": 0.0625,
         "p_holm": 0.6875,
         "plain_rate": 0.0,
         "abstain_rate": 0.02976190476190476
        },
        {
         "n_pairs": 168,
         "n_ties": 164,
         "plain_only": 0,
         "abstain_only": 4,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.023809523809523808
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gemma4:26b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 167,
         "plain_only": 0,
         "abstain_only": 1,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.011904761904761904,
         "abstain_rate": 0.017857142857142856
        },
        {
         "n_pairs": 168,
         "n_ties": 166,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.011904761904761904,
         "abstain_rate": 0.023809523809523808
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gpt-oss:20b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 167,
         "plain_only": 0,
         "abstain_only": 1,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.005952380952380952
        },
        {
         "n_pairs": 168,
         "n_ties": 168,
         "plain_only": 0,
         "abstain_only": 0,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.0
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gpt-oss:120b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 166,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.011904761904761904
        },
        {
         "n_pairs": 168,
         "n_ties": 166,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.011904761904761904
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "deepseek-r1:8b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 153,
         "plain_only": 2,
         "abstain_only": 13,
         "p": 0.00738525390625,
         "p_holm": 0.11077880859375,
         "plain_rate": 0.011904761904761904,
         "abstain_rate": 0.07738095238095238
        },
        {
         "n_pairs": 168,
         "n_ties": 150,
         "plain_only": 0,
         "abstain_only": 18,
         "p": 7.62939453125e-06,
         "p_holm": 0.0001220703125,
         "plain_rate": 0.011904761904761904,
         "abstain_rate": 0.11904761904761904
        }
       ],
       "p_holm_max": 0.11077880859375,
       "significant_both": false,
       "plain_greater_both": false
      },
      "deepseek-r1:14b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 162,
         "plain_only": 0,
         "abstain_only": 6,
         "p": 0.03125,
         "p_holm": 0.40625,
         "plain_rate": 0.0,
         "abstain_rate": 0.03571428571428571
        },
        {
         "n_pairs": 168,
         "n_ties": 163,
         "plain_only": 0,
         "abstain_only": 5,
         "p": 0.0625,
         "p_holm": 0.75,
         "plain_rate": 0.005952380952380952,
         "abstain_rate": 0.03571428571428571
        }
       ],
       "p_holm_max": 0.75,
       "significant_both": false,
       "plain_greater_both": false
      },
      "llama3.1:8b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 160,
         "plain_only": 0,
         "abstain_only": 8,
         "p": 0.0078125,
         "p_holm": 0.11077880859375,
         "plain_rate": 0.0,
         "abstain_rate": 0.047619047619047616
        },
        {
         "n_pairs": 168,
         "n_ties": 160,
         "plain_only": 0,
         "abstain_only": 8,
         "p": 0.0078125,
         "p_holm": 0.109375,
         "plain_rate": 0.0,
         "abstain_rate": 0.047619047619047616
        }
       ],
       "p_holm_max": 0.11077880859375,
       "significant_both": false,
       "plain_greater_both": false
      },
      "mistral-small3.2:24b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 164,
         "plain_only": 0,
         "abstain_only": 4,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.023809523809523808
        },
        {
         "n_pairs": 168,
         "n_ties": 164,
         "plain_only": 0,
         "abstain_only": 4,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.023809523809523808
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "phi4:14b": {
       "runs": [
        {
         "n_pairs": 168,
         "n_ties": 152,
         "plain_only": 0,
         "abstain_only": 16,
         "p": 3.0517578125e-05,
         "p_holm": 0.00048828125,
         "plain_rate": 0.0,
         "abstain_rate": 0.09523809523809523
        },
        {
         "n_pairs": 168,
         "n_ties": 152,
         "plain_only": 0,
         "abstain_only": 16,
         "p": 3.0517578125e-05,
         "p_holm": 0.000457763671875,
         "plain_rate": 0.0,
         "abstain_rate": 0.09523809523809523
        }
       ],
       "p_holm_max": 0.00048828125,
       "significant_both": true,
       "plain_greater_both": false
      }
     },
     "n_significant_both": 1
    }
   },
   "tradeoff": {
    "qwen3:8b": {
     "drop": [
      64.28571428571429,
      62.5
     ],
     "rise": [
      2.380952380952381,
      2.380952380952381
     ],
     "correct_change": [
      -2.380952380952381,
      -1.7857142857142858
     ],
     "disp": {
      "drop": "62.5〜64.3",
      "rise": "2.4",
      "correct_change": "-2.4〜-1.8",
      "drop0": "63〜64",
      "rise0": "2"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "qwen3:14b": {
     "drop": [
      52.38095238095238,
      55.357142857142854
     ],
     "rise": [
      1.1904761904761905,
      1.1904761904761905
     ],
     "correct_change": [
      -0.5952380952380952,
      -0.5952380952380952
     ],
     "disp": {
      "drop": "52.4〜55.4",
      "rise": "1.2",
      "correct_change": "-0.6",
      "drop0": "52〜55",
      "rise0": "1"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "qwen3:30b": {
     "drop": [
      42.857142857142854,
      38.69047619047619
     ],
     "rise": [
      1.1904761904761905,
      0.5952380952380952
     ],
     "correct_change": [
      2.380952380952381,
      0.0
     ],
     "disp": {
      "drop": "38.7〜42.9",
      "rise": "0.6〜1.2",
      "correct_change": "0.0〜2.4",
      "drop0": "39〜43",
      "rise0": "1"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "qwen3.5:9b": {
     "drop": [
      27.976190476190474,
      29.166666666666668
     ],
     "rise": [
      3.5714285714285716,
      3.5714285714285716
     ],
     "correct_change": [
      -1.7857142857142858,
      -2.380952380952381
     ],
     "disp": {
      "drop": "28.0〜29.2",
      "rise": "3.6",
      "correct_change": "-2.4〜-1.8",
      "drop0": "28〜29",
      "rise0": "4"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "qwen3.5:27b": {
     "drop": [
      19.642857142857142,
      19.642857142857142
     ],
     "rise": [
      1.7857142857142858,
      2.380952380952381
     ],
     "correct_change": [
      -1.7857142857142858,
      -2.380952380952381
     ],
     "disp": {
      "drop": "19.6",
      "rise": "1.8〜2.4",
      "correct_change": "-2.4〜-1.8",
      "drop0": "20",
      "rise0": "2"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "gemma3:12b": {
     "drop": [
      23.80952380952381,
      22.023809523809526
     ],
     "rise": [
      2.380952380952381,
      2.380952380952381
     ],
     "correct_change": [
      -2.380952380952381,
      -1.7857142857142858
     ],
     "disp": {
      "drop": "22.0〜23.8",
      "rise": "2.4",
      "correct_change": "-2.4〜-1.8",
      "drop0": "22〜24",
      "rise0": "2"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "gemma3:27b": {
     "drop": [
      28.571428571428573,
      27.38095238095238
     ],
     "rise": [
      1.1904761904761905,
      1.1904761904761905
     ],
     "correct_change": [
      0.5952380952380952,
      0.5952380952380952
     ],
     "disp": {
      "drop": "27.4〜28.6",
      "rise": "1.2",
      "correct_change": "0.6",
      "drop0": "27〜29",
      "rise0": "1"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "gemma4:12b": {
     "drop": [
      23.214285714285715,
      22.61904761904762
     ],
     "rise": [
      2.9761904761904763,
      2.380952380952381
     ],
     "correct_change": [
      -2.380952380952381,
      -1.7857142857142858
     ],
     "disp": {
      "drop": "22.6〜23.2",
      "rise": "2.4〜3.0",
      "correct_change": "-2.4〜-1.8",
      "drop0": "23",
      "rise0": "2〜3"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "gemma4:26b": {
     "drop": [
      13.69047619047619,
      11.30952380952381
     ],
     "rise": [
      0.5952380952380952,
      1.1904761904761905
     ],
     "correct_change": [
      -1.1904761904761905,
      -1.7857142857142858
     ],
     "disp": {
      "drop": "11.3〜13.7",
      "rise": "0.6〜1.2",
      "correct_change": "-1.8〜-1.2",
      "drop0": "11〜14",
      "rise0": "1"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "gpt-oss:20b": {
     "drop": [
      52.38095238095238,
      54.76190476190476
     ],
     "rise": [
      0.5952380952380952,
      0.0
     ],
     "correct_change": [
      -0.5952380952380952,
      -0.5952380952380952
     ],
     "disp": {
      "drop": "52.4〜54.8",
      "rise": "0.0〜0.6",
      "correct_change": "-0.6",
      "drop0": "52〜55",
      "rise0": "0〜1"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": false,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "gpt-oss:120b": {
     "drop": [
      62.5,
      63.69047619047619
     ],
     "rise": [
      1.1904761904761905,
      1.1904761904761905
     ],
     "correct_change": [
      -0.5952380952380952,
      0.0
     ],
     "disp": {
      "drop": "62.5〜63.7",
      "rise": "1.2",
      "correct_change": "-0.6〜0.0",
      "drop0": "63〜64",
      "rise0": "1"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "deepseek-r1:8b": {
     "drop": [
      27.38095238095238,
      27.38095238095238
     ],
     "rise": [
      6.5476190476190474,
      10.714285714285714
     ],
     "correct_change": [
      -0.5952380952380952,
      -7.738095238095238
     ],
     "disp": {
      "drop": "27.4",
      "rise": "6.5〜10.7",
      "correct_change": "-7.7〜-0.6",
      "drop0": "27",
      "rise0": "7〜11"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "deepseek-r1:14b": {
     "drop": [
      39.88095238095238,
      38.69047619047619
     ],
     "rise": [
      3.5714285714285716,
      2.9761904761904763
     ],
     "correct_change": [
      -1.1904761904761905,
      1.1904761904761905
     ],
     "disp": {
      "drop": "38.7〜39.9",
      "rise": "3.0〜3.6",
      "correct_change": "-1.2〜1.2",
      "drop0": "39〜40",
      "rise0": "3〜4"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "llama3.1:8b": {
     "drop": [
      63.69047619047619,
      64.28571428571429
     ],
     "rise": [
      4.761904761904762,
      4.761904761904762
     ],
     "correct_change": [
      -11.30952380952381,
      -12.5
     ],
     "disp": {
      "drop": "63.7〜64.3",
      "rise": "4.8",
      "correct_change": "-12.5〜-11.3",
      "drop0": "64",
      "rise0": "5"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "mistral-small3.2:24b": {
     "drop": [
      42.857142857142854,
      44.04761904761905
     ],
     "rise": [
      2.380952380952381,
      2.380952380952381
     ],
     "correct_change": [
      -1.1904761904761905,
      -1.1904761904761905
     ],
     "disp": {
      "drop": "42.9〜44.0",
      "rise": "2.4",
      "correct_change": "-1.2",
      "drop0": "43〜44",
      "rise0": "2"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "phi4:14b": {
     "drop": [
      33.333333333333336,
      32.142857142857146
     ],
     "rise": [
      9.523809523809524,
      9.523809523809524
     ],
     "correct_change": [
      -8.333333333333334,
      -8.928571428571429
     ],
     "disp": {
      "drop": "32.1〜33.3",
      "rise": "9.5",
      "correct_change": "-8.9〜-8.3",
      "drop0": "32〜33",
      "rise0": "10"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": true
    }
   },
   "order_by_near_plain": [
    "qwen3:8b",
    "gpt-oss:20b",
    "llama3.1:8b",
    "gpt-oss:120b",
    "qwen3:14b",
    "qwen3:30b",
    "mistral-small3.2:24b",
    "deepseek-r1:14b",
    "gemma3:27b",
    "deepseek-r1:8b",
    "gemma3:12b",
    "phi4:14b",
    "qwen3.5:9b",
    "gemma4:12b",
    "gemma4:26b",
    "qwen3.5:27b"
   ]
  },
  "excluded": {
   "n_questions": 129,
   "cells": {
    "qwen3:8b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         121,
         120
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         8,
         9
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         8,
         9
        ]
       },
       "rates": {
        "correct": [
         0.937984496124031,
         0.9302325581395349
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.06201550387596899,
         0.06976744186046512
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.06201550387596899,
         0.06976744186046512
        ]
       },
       "disp": {
        "correct": {
         "p0": "93〜94",
         "p1": "93.0〜93.8",
         "count": "120〜121"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "6〜7",
         "p1": "6.2〜7.0",
         "count": "8〜9"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "6〜7",
         "p1": "6.2〜7.0",
         "count": "8〜9"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         18,
         20
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         110,
         108
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         110,
         108
        ]
       },
       "rates": {
        "correct": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "abstain": [
         0.13953488372093023,
         0.15503875968992248
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.8527131782945736,
         0.8372093023255814
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.8527131782945736,
         0.8372093023255814
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "abstain": {
         "p0": "14〜16",
         "p1": "14.0〜15.5",
         "count": "18〜20"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "84〜85",
         "p1": "83.7〜85.3",
         "count": "108〜110"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "84〜85",
         "p1": "83.7〜85.3",
         "count": "108〜110"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         73,
         71
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         56,
         58
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         56,
         58
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.5658914728682171,
         0.5503875968992248
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.43410852713178294,
         0.4496124031007752
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.43410852713178294,
         0.4496124031007752
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "55〜57",
         "p1": "55.0〜56.6",
         "count": "71〜73"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "43〜45",
         "p1": "43.4〜45.0",
         "count": "56〜58"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "43〜45",
         "p1": "43.4〜45.0",
         "count": "56〜58"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         117,
         117
        ],
        "abstain": [
         3,
         3
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         9,
         9
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         9,
         9
        ]
       },
       "rates": {
        "correct": [
         0.9069767441860465,
         0.9069767441860465
        ],
        "abstain": [
         0.023255813953488372,
         0.023255813953488372
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.06976744186046512,
         0.06976744186046512
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.06976744186046512,
         0.06976744186046512
        ]
       },
       "disp": {
        "correct": {
         "p0": "91",
         "p1": "90.7",
         "count": "117"
        },
        "abstain": {
         "p0": "2",
         "p1": "2.3",
         "count": "3"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "7",
         "p1": "7.0",
         "count": "9"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "7",
         "p1": "7.0",
         "count": "9"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         110,
         110
        ],
        "hedged": [
         1,
         1
        ],
        "other": [
         18,
         18
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         19,
         19
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.8527131782945736,
         0.8527131782945736
        ],
        "hedged": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "other": [
         0.13953488372093023,
         0.13953488372093023
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.14728682170542637,
         0.14728682170542637
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "85",
         "p1": "85.3",
         "count": "110"
        },
        "hedged": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "other": {
         "p0": "14",
         "p1": "14.0",
         "count": "18"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "15",
         "p1": "14.7",
         "count": "19"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         118,
         120
        ],
        "abstain": [
         4,
         5
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         7,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         7,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9147286821705426,
         0.9302325581395349
        ],
        "abstain": [
         0.031007751937984496,
         0.03875968992248062
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.05426356589147287,
         0.031007751937984496
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.05426356589147287,
         0.031007751937984496
        ]
       },
       "disp": {
        "correct": {
         "p0": "91〜93",
         "p1": "91.5〜93.0",
         "count": "118〜120"
        },
        "abstain": {
         "p0": "3〜4",
         "p1": "3.1〜3.9",
         "count": "4〜5"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3〜5",
         "p1": "3.1〜5.4",
         "count": "4〜7"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3〜5",
         "p1": "3.1〜5.4",
         "count": "4〜7"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         112,
         111
        ],
        "hedged": [
         0,
         1
        ],
        "other": [
         16,
         16
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         16,
         17
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.8682170542635659,
         0.8604651162790697
        ],
        "hedged": [
         0.0,
         0.007751937984496124
        ],
        "other": [
         0.12403100775193798,
         0.12403100775193798
        ],
        "unresolved": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "answered": [
         0.12403100775193798,
         0.13178294573643412
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "86〜87",
         "p1": "86.0〜86.8",
         "count": "111〜112"
        },
        "hedged": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "other": {
         "p0": "12",
         "p1": "12.4",
         "count": "16"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "answered": {
         "p0": "12〜13",
         "p1": "12.4〜13.2",
         "count": "16〜17"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "qwen3:14b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         126,
         125
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9767441860465116,
         0.9689922480620154
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023255813953488372,
         0.031007751937984496
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023255813953488372,
         0.031007751937984496
        ]
       },
       "disp": {
        "correct": {
         "p0": "97〜98",
         "p1": "96.9〜97.7",
         "count": "125〜126"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2〜3",
         "p1": "2.3〜3.1",
         "count": "3〜4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2〜3",
         "p1": "2.3〜3.1",
         "count": "3〜4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         37,
         33
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         92,
         96
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         92,
         96
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.2868217054263566,
         0.2558139534883721
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.7131782945736435,
         0.7441860465116279
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.7131782945736435,
         0.7441860465116279
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "26〜29",
         "p1": "25.6〜28.7",
         "count": "33〜37"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "71〜74",
         "p1": "71.3〜74.4",
         "count": "92〜96"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "71〜74",
         "p1": "71.3〜74.4",
         "count": "92〜96"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         99,
         99
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         30,
         30
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         30,
         30
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.7674418604651163,
         0.7674418604651163
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.23255813953488372,
         0.23255813953488372
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.23255813953488372,
         0.23255813953488372
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "77",
         "p1": "76.7",
         "count": "99"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "23",
         "p1": "23.3",
         "count": "30"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "23",
         "p1": "23.3",
         "count": "30"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         125,
         124
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         3
        ]
       },
       "rates": {
        "correct": [
         0.9689922480620154,
         0.9612403100775194
        ],
        "abstain": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.015503875968992248,
         0.023255813953488372
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.015503875968992248,
         0.023255813953488372
        ]
       },
       "disp": {
        "correct": {
         "p0": "96〜97",
         "p1": "96.1〜96.9",
         "count": "124〜125"
        },
        "abstain": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         111,
         111
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         18,
         18
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         18,
         18
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.8604651162790697,
         0.8604651162790697
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.13953488372093023,
         0.13953488372093023
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.13953488372093023,
         0.13953488372093023
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "86",
         "p1": "86.0",
         "count": "111"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "14",
         "p1": "14.0",
         "count": "18"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "14",
         "p1": "14.0",
         "count": "18"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         123,
         122
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         5
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         5
        ]
       },
       "rates": {
        "correct": [
         0.9534883720930233,
         0.9457364341085271
        ],
        "abstain": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.031007751937984496,
         0.03875968992248062
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.031007751937984496,
         0.03875968992248062
        ]
       },
       "disp": {
        "correct": {
         "p0": "95",
         "p1": "94.6〜95.3",
         "count": "122〜123"
        },
        "abstain": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3〜4",
         "p1": "3.1〜3.9",
         "count": "4〜5"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3〜4",
         "p1": "3.1〜3.9",
         "count": "4〜5"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         96,
         98
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         33,
         31
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         33,
         31
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.7441860465116279,
         0.7596899224806202
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.2558139534883721,
         0.24031007751937986
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.2558139534883721,
         0.24031007751937986
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "74〜76",
         "p1": "74.4〜76.0",
         "count": "96〜98"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "24〜26",
         "p1": "24.0〜25.6",
         "count": "31〜33"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "24〜26",
         "p1": "24.0〜25.6",
         "count": "31〜33"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         128,
         128
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9922480620155039,
         0.9922480620155039
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.007751937984496124,
         0.007751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "99.2",
         "count": "128"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        }
       }
      }
     }
    },
    "qwen3:30b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         121,
         121
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         6,
         6
        ],
        "unresolved": [
         2,
         2
        ],
        "answered": [
         6,
         6
        ]
       },
       "rates": {
        "correct": [
         0.937984496124031,
         0.937984496124031
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.046511627906976744,
         0.046511627906976744
        ],
        "unresolved": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "answered": [
         0.046511627906976744,
         0.046511627906976744
        ]
       },
       "disp": {
        "correct": {
         "p0": "94",
         "p1": "93.8",
         "count": "121"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5",
         "p1": "4.7",
         "count": "6"
        },
        "unresolved": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "answered": {
         "p0": "5",
         "p1": "4.7",
         "count": "6"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         19,
         18
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         81,
         75
        ],
        "unresolved": [
         28,
         35
        ],
        "answered": [
         81,
         75
        ]
       },
       "rates": {
        "correct": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "abstain": [
         0.14728682170542637,
         0.13953488372093023
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.627906976744186,
         0.5813953488372093
        ],
        "unresolved": [
         0.21705426356589147,
         0.2713178294573643
        ],
        "answered": [
         0.627906976744186,
         0.5813953488372093
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "abstain": {
         "p0": "14〜15",
         "p1": "14.0〜14.7",
         "count": "18〜19"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "58〜63",
         "p1": "58.1〜62.8",
         "count": "75〜81"
        },
        "unresolved": {
         "p0": "22〜27",
         "p1": "21.7〜27.1",
         "count": "28〜35"
        },
        "answered": {
         "p0": "58〜63",
         "p1": "58.1〜62.8",
         "count": "75〜81"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         79,
         83
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         43,
         40
        ],
        "unresolved": [
         7,
         6
        ],
        "answered": [
         43,
         40
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.6124031007751938,
         0.6434108527131783
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.3333333333333333,
         0.31007751937984496
        ],
        "unresolved": [
         0.05426356589147287,
         0.046511627906976744
        ],
        "answered": [
         0.3333333333333333,
         0.31007751937984496
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "61〜64",
         "p1": "61.2〜64.3",
         "count": "79〜83"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "31〜33",
         "p1": "31.0〜33.3",
         "count": "40〜43"
        },
        "unresolved": {
         "p0": "5",
         "p1": "4.7〜5.4",
         "count": "6〜7"
        },
        "answered": {
         "p0": "31〜33",
         "p1": "31.0〜33.3",
         "count": "40〜43"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         123,
         121
        ],
        "abstain": [
         2,
         1
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         6
        ],
        "unresolved": [
         0,
         1
        ],
        "answered": [
         4,
         6
        ]
       },
       "rates": {
        "correct": [
         0.9534883720930233,
         0.937984496124031
        ],
        "abstain": [
         0.015503875968992248,
         0.007751937984496124
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.031007751937984496,
         0.046511627906976744
        ],
        "unresolved": [
         0.0,
         0.007751937984496124
        ],
        "answered": [
         0.031007751937984496,
         0.046511627906976744
        ]
       },
       "disp": {
        "correct": {
         "p0": "94〜95",
         "p1": "93.8〜95.3",
         "count": "121〜123"
        },
        "abstain": {
         "p0": "1〜2",
         "p1": "0.8〜1.6",
         "count": "1〜2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3〜5",
         "p1": "3.1〜4.7",
         "count": "4〜6"
        },
        "unresolved": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "answered": {
         "p0": "3〜5",
         "p1": "3.1〜4.7",
         "count": "4〜6"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         103,
         103
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         22,
         23
        ],
        "unresolved": [
         3,
         2
        ],
        "answered": [
         22,
         23
        ]
       },
       "rates": {
        "correct": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "abstain": [
         0.7984496124031008,
         0.7984496124031008
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.17054263565891473,
         0.17829457364341086
        ],
        "unresolved": [
         0.023255813953488372,
         0.015503875968992248
        ],
        "answered": [
         0.17054263565891473,
         0.17829457364341086
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "abstain": {
         "p0": "80",
         "p1": "79.8",
         "count": "103"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "17〜18",
         "p1": "17.1〜17.8",
         "count": "22〜23"
        },
        "unresolved": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        },
        "answered": {
         "p0": "17〜18",
         "p1": "17.1〜17.8",
         "count": "22〜23"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         128,
         128
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9922480620155039,
         0.9922480620155039
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.007751937984496124,
         0.007751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "99.2",
         "count": "128"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         126,
         124
        ],
        "abstain": [
         1,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         3
        ]
       },
       "rates": {
        "correct": [
         0.9767441860465116,
         0.9612403100775194
        ],
        "abstain": [
         0.007751937984496124,
         0.015503875968992248
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.015503875968992248,
         0.023255813953488372
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.015503875968992248,
         0.023255813953488372
        ]
       },
       "disp": {
        "correct": {
         "p0": "96〜98",
         "p1": "96.1〜97.7",
         "count": "124〜126"
        },
        "abstain": {
         "p0": "1〜2",
         "p1": "0.8〜1.6",
         "count": "1〜2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         1
        ],
        "abstain": [
         106,
         100
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         19,
         20
        ],
        "unresolved": [
         4,
         8
        ],
        "answered": [
         19,
         20
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.007751937984496124
        ],
        "abstain": [
         0.8217054263565892,
         0.7751937984496124
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.14728682170542637,
         0.15503875968992248
        ],
        "unresolved": [
         0.031007751937984496,
         0.06201550387596899
        ],
        "answered": [
         0.14728682170542637,
         0.15503875968992248
        ]
       },
       "disp": {
        "correct": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "abstain": {
         "p0": "78〜82",
         "p1": "77.5〜82.2",
         "count": "100〜106"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "15〜16",
         "p1": "14.7〜15.5",
         "count": "19〜20"
        },
        "unresolved": {
         "p0": "3〜6",
         "p1": "3.1〜6.2",
         "count": "4〜8"
        },
        "answered": {
         "p0": "15〜16",
         "p1": "14.7〜15.5",
         "count": "19〜20"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         128,
         128
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9922480620155039,
         0.9922480620155039
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "99.2",
         "count": "128"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "qwen3.5:9b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         124,
         125
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         2
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         2
        ]
       },
       "rates": {
        "correct": [
         0.9612403100775194,
         0.9689922480620154
        ],
        "abstain": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023255813953488372,
         0.015503875968992248
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023255813953488372,
         0.015503875968992248
        ]
       },
       "disp": {
        "correct": {
         "p0": "96〜97",
         "p1": "96.1〜96.9",
         "count": "124〜125"
        },
        "abstain": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         80,
         79
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         48,
         49
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         48,
         49
        ]
       },
       "rates": {
        "correct": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "abstain": [
         0.6201550387596899,
         0.6124031007751938
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.37209302325581395,
         0.3798449612403101
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.37209302325581395,
         0.3798449612403101
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "abstain": {
         "p0": "61〜62",
         "p1": "61.2〜62.0",
         "count": "79〜80"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "37〜38",
         "p1": "37.2〜38.0",
         "count": "48〜49"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "37〜38",
         "p1": "37.2〜38.0",
         "count": "48〜49"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         122,
         123
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         7,
         6
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         7,
         6
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9457364341085271,
         0.9534883720930233
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.05426356589147287,
         0.046511627906976744
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.05426356589147287,
         0.046511627906976744
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "95",
         "p1": "94.6〜95.3",
         "count": "122〜123"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5",
         "p1": "4.7〜5.4",
         "count": "6〜7"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "5",
         "p1": "4.7〜5.4",
         "count": "6〜7"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         122,
         122
        ],
        "abstain": [
         7,
         7
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.9457364341085271,
         0.9457364341085271
        ],
        "abstain": [
         0.05426356589147287,
         0.05426356589147287
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "95",
         "p1": "94.6",
         "count": "122"
        },
        "abstain": {
         "p0": "5",
         "p1": "5.4",
         "count": "7"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         118,
         118
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         11,
         11
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         11,
         11
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9147286821705426,
         0.9147286821705426
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.08527131782945736,
         0.08527131782945736
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.08527131782945736,
         0.08527131782945736
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "91",
         "p1": "91.5",
         "count": "118"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "9",
         "p1": "8.5",
         "count": "11"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "9",
         "p1": "8.5",
         "count": "11"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         81,
         81
        ],
        "abstain": [
         46,
         46
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         2
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         2
        ]
       },
       "rates": {
        "correct": [
         0.627906976744186,
         0.627906976744186
        ],
        "abstain": [
         0.35658914728682173,
         0.35658914728682173
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.015503875968992248,
         0.015503875968992248
        ]
       },
       "disp": {
        "correct": {
         "p0": "63",
         "p1": "62.8",
         "count": "81"
        },
        "abstain": {
         "p0": "36",
         "p1": "35.7",
         "count": "46"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         124,
         124
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         5,
         5
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         5,
         5
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9612403100775194,
         0.9612403100775194
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.03875968992248062,
         0.03875968992248062
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.03875968992248062,
         0.03875968992248062
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "96",
         "p1": "96.1",
         "count": "124"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4",
         "p1": "3.9",
         "count": "5"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "4",
         "p1": "3.9",
         "count": "5"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "qwen3.5:27b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         129,
         129
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         1.0,
         1.0
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         106,
         106
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         23,
         23
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         23,
         23
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.8217054263565892,
         0.8217054263565892
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.17829457364341086,
         0.17829457364341086
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.17829457364341086,
         0.17829457364341086
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "82",
         "p1": "82.2",
         "count": "106"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "18",
         "p1": "17.8",
         "count": "23"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "18",
         "p1": "17.8",
         "count": "23"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         128,
         127
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         2
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         2
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9922480620155039,
         0.9844961240310077
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.007751937984496124,
         0.015503875968992248
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.007751937984496124,
         0.015503875968992248
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "98〜99",
         "p1": "98.4〜99.2",
         "count": "127〜128"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1〜2",
         "p1": "0.8〜1.6",
         "count": "1〜2"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1〜2",
         "p1": "0.8〜1.6",
         "count": "1〜2"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         126,
         126
        ],
        "abstain": [
         3,
         3
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.9767441860465116,
         0.9767441860465116
        ],
        "abstain": [
         0.023255813953488372,
         0.023255813953488372
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "98",
         "p1": "97.7",
         "count": "126"
        },
        "abstain": {
         "p0": "2",
         "p1": "2.3",
         "count": "3"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         128,
         128
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9922480620155039,
         0.9922480620155039
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.007751937984496124,
         0.007751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "99.2",
         "count": "128"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         129,
         129
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         1.0,
         1.0
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         124,
         124
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         5,
         5
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         5,
         5
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9612403100775194,
         0.9612403100775194
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.03875968992248062,
         0.03875968992248062
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.03875968992248062,
         0.03875968992248062
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "96",
         "p1": "96.1",
         "count": "124"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4",
         "p1": "3.9",
         "count": "5"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "4",
         "p1": "3.9",
         "count": "5"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "gemma3:12b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         125,
         125
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9689922480620154,
         0.9689922480620154
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.031007751937984496,
         0.031007751937984496
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.031007751937984496,
         0.031007751937984496
        ]
       },
       "disp": {
        "correct": {
         "p0": "97",
         "p1": "96.9",
         "count": "125"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3",
         "p1": "3.1",
         "count": "4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3",
         "p1": "3.1",
         "count": "4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         81,
         82
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         47,
         45
        ],
        "unresolved": [
         1,
         2
        ],
        "answered": [
         47,
         45
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.627906976744186,
         0.6356589147286822
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.3643410852713178,
         0.3488372093023256
        ],
        "unresolved": [
         0.007751937984496124,
         0.015503875968992248
        ],
        "answered": [
         0.3643410852713178,
         0.3488372093023256
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "63〜64",
         "p1": "62.8〜63.6",
         "count": "81〜82"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "35〜36",
         "p1": "34.9〜36.4",
         "count": "45〜47"
        },
        "unresolved": {
         "p0": "1〜2",
         "p1": "0.8〜1.6",
         "count": "1〜2"
        },
        "answered": {
         "p0": "35〜36",
         "p1": "34.9〜36.4",
         "count": "45〜47"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         125,
         126
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         3
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9689922480620154,
         0.9767441860465116
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.031007751937984496,
         0.023255813953488372
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.031007751937984496,
         0.023255813953488372
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "97〜98",
         "p1": "96.9〜97.7",
         "count": "125〜126"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2〜3",
         "p1": "2.3〜3.1",
         "count": "3〜4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2〜3",
         "p1": "2.3〜3.1",
         "count": "3〜4"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         122,
         123
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         5,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         5,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9457364341085271,
         0.9534883720930233
        ],
        "abstain": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.03875968992248062,
         0.031007751937984496
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.03875968992248062,
         0.031007751937984496
        ]
       },
       "disp": {
        "correct": {
         "p0": "95",
         "p1": "94.6〜95.3",
         "count": "122〜123"
        },
        "abstain": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3〜4",
         "p1": "3.1〜3.9",
         "count": "4〜5"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3〜4",
         "p1": "3.1〜3.9",
         "count": "4〜5"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         112,
         111
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         17,
         18
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         17,
         18
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.8682170542635659,
         0.8604651162790697
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.13178294573643412,
         0.13953488372093023
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.13178294573643412,
         0.13953488372093023
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "86〜87",
         "p1": "86.0〜86.8",
         "count": "111〜112"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "13〜14",
         "p1": "13.2〜14.0",
         "count": "17〜18"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "13〜14",
         "p1": "13.2〜14.0",
         "count": "17〜18"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         125,
         124
        ],
        "abstain": [
         3,
         4
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.9689922480620154,
         0.9612403100775194
        ],
        "abstain": [
         0.023255813953488372,
         0.031007751937984496
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.007751937984496124,
         0.007751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "96〜97",
         "p1": "96.1〜96.9",
         "count": "124〜125"
        },
        "abstain": {
         "p0": "2〜3",
         "p1": "2.3〜3.1",
         "count": "3〜4"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         116,
         116
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         13,
         13
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         13,
         13
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.8992248062015504,
         0.8992248062015504
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.10077519379844961,
         0.10077519379844961
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.10077519379844961,
         0.10077519379844961
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "90",
         "p1": "89.9",
         "count": "116"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "10",
         "p1": "10.1",
         "count": "13"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "10",
         "p1": "10.1",
         "count": "13"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "gemma3:27b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         125,
         125
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9689922480620154,
         0.9689922480620154
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.031007751937984496,
         0.031007751937984496
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.031007751937984496,
         0.031007751937984496
        ]
       },
       "disp": {
        "correct": {
         "p0": "97",
         "p1": "96.9",
         "count": "125"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3",
         "p1": "3.1",
         "count": "4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3",
         "p1": "3.1",
         "count": "4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         2,
         2
        ],
        "abstain": [
         63,
         65
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         61,
         59
        ],
        "unresolved": [
         3,
         3
        ],
        "answered": [
         61,
         59
        ]
       },
       "rates": {
        "correct": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "abstain": [
         0.4883720930232558,
         0.5038759689922481
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.4728682170542636,
         0.4573643410852713
        ],
        "unresolved": [
         0.023255813953488372,
         0.023255813953488372
        ],
        "answered": [
         0.4728682170542636,
         0.4573643410852713
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "abstain": {
         "p0": "49〜50",
         "p1": "48.8〜50.4",
         "count": "63〜65"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "46〜47",
         "p1": "45.7〜47.3",
         "count": "59〜61"
        },
        "unresolved": {
         "p0": "2",
         "p1": "2.3",
         "count": "3"
        },
        "answered": {
         "p0": "46〜47",
         "p1": "45.7〜47.3",
         "count": "59〜61"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         123,
         123
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         6,
         6
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         6,
         6
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9534883720930233,
         0.9534883720930233
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.046511627906976744,
         0.046511627906976744
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.046511627906976744,
         0.046511627906976744
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "95",
         "p1": "95.3",
         "count": "123"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5",
         "p1": "4.7",
         "count": "6"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "5",
         "p1": "4.7",
         "count": "6"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         125,
         125
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         2
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         2
        ]
       },
       "rates": {
        "correct": [
         0.9689922480620154,
         0.9689922480620154
        ],
        "abstain": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.015503875968992248,
         0.015503875968992248
        ]
       },
       "disp": {
        "correct": {
         "p0": "97",
         "p1": "96.9",
         "count": "125"
        },
        "abstain": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         104,
         105
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         24,
         23
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         24,
         23
        ]
       },
       "rates": {
        "correct": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "abstain": [
         0.8062015503875969,
         0.813953488372093
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.18604651162790697,
         0.17829457364341086
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.18604651162790697,
         0.17829457364341086
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "abstain": {
         "p0": "81",
         "p1": "80.6〜81.4",
         "count": "104〜105"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "18〜19",
         "p1": "17.8〜18.6",
         "count": "23〜24"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "18〜19",
         "p1": "17.8〜18.6",
         "count": "23〜24"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         126,
         126
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         3
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9767441860465116,
         0.9767441860465116
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023255813953488372,
         0.023255813953488372
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023255813953488372,
         0.023255813953488372
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "98",
         "p1": "97.7",
         "count": "126"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "2.3",
         "count": "3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "2.3",
         "count": "3"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         126,
         126
        ],
        "abstain": [
         1,
         1
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         2
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         2
        ]
       },
       "rates": {
        "correct": [
         0.9767441860465116,
         0.9767441860465116
        ],
        "abstain": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.015503875968992248,
         0.015503875968992248
        ]
       },
       "disp": {
        "correct": {
         "p0": "98",
         "p1": "97.7",
         "count": "126"
        },
        "abstain": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         98,
         99
        ],
        "hedged": [
         1,
         0
        ],
        "other": [
         29,
         29
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         30,
         29
        ]
       },
       "rates": {
        "correct": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "abstain": [
         0.7596899224806202,
         0.7674418604651163
        ],
        "hedged": [
         0.007751937984496124,
         0.0
        ],
        "other": [
         0.2248062015503876,
         0.2248062015503876
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.23255813953488372,
         0.2248062015503876
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "abstain": {
         "p0": "76〜77",
         "p1": "76.0〜76.7",
         "count": "98〜99"
        },
        "hedged": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "other": {
         "p0": "22",
         "p1": "22.5",
         "count": "29"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "22〜23",
         "p1": "22.5〜23.3",
         "count": "29〜30"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         126,
         126
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         3
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9767441860465116,
         0.9767441860465116
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023255813953488372,
         0.023255813953488372
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023255813953488372,
         0.023255813953488372
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "98",
         "p1": "97.7",
         "count": "126"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "2.3",
         "count": "3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "2.3",
         "count": "3"
        }
       }
      }
     }
    },
    "gemma4:12b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         127,
         127
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         2
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         2
        ]
       },
       "rates": {
        "correct": [
         0.9844961240310077,
         0.9844961240310077
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.015503875968992248,
         0.015503875968992248
        ]
       },
       "disp": {
        "correct": {
         "p0": "98",
         "p1": "98.4",
         "count": "127"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         90,
         91
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         37,
         37
        ],
        "unresolved": [
         2,
         1
        ],
        "answered": [
         37,
         37
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.6976744186046512,
         0.7054263565891473
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.2868217054263566,
         0.2868217054263566
        ],
        "unresolved": [
         0.015503875968992248,
         0.007751937984496124
        ],
        "answered": [
         0.2868217054263566,
         0.2868217054263566
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "70〜71",
         "p1": "69.8〜70.5",
         "count": "90〜91"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "29",
         "p1": "28.7",
         "count": "37"
        },
        "unresolved": {
         "p0": "1〜2",
         "p1": "0.8〜1.6",
         "count": "1〜2"
        },
        "answered": {
         "p0": "29",
         "p1": "28.7",
         "count": "37"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         127,
         127
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         2
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         2
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9844961240310077,
         0.9844961240310077
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.015503875968992248,
         0.015503875968992248
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "98",
         "p1": "98.4",
         "count": "127"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         123,
         124
        ],
        "abstain": [
         5,
         4
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.9534883720930233,
         0.9612403100775194
        ],
        "abstain": [
         0.03875968992248062,
         0.031007751937984496
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.007751937984496124,
         0.007751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "95〜96",
         "p1": "95.3〜96.1",
         "count": "123〜124"
        },
        "abstain": {
         "p0": "3〜4",
         "p1": "3.1〜3.9",
         "count": "4〜5"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         119,
         118
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         10,
         11
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         10,
         11
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9224806201550387,
         0.9147286821705426
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.07751937984496124,
         0.08527131782945736
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.07751937984496124,
         0.08527131782945736
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "91〜92",
         "p1": "91.5〜92.2",
         "count": "118〜119"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "8〜9",
         "p1": "7.8〜8.5",
         "count": "10〜11"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "8〜9",
         "p1": "7.8〜8.5",
         "count": "10〜11"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         126,
         126
        ],
        "abstain": [
         3,
         3
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.9767441860465116,
         0.9767441860465116
        ],
        "abstain": [
         0.023255813953488372,
         0.023255813953488372
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "98",
         "p1": "97.7",
         "count": "126"
        },
        "abstain": {
         "p0": "2",
         "p1": "2.3",
         "count": "3"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         115,
         115
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         14,
         14
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         14,
         14
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.8914728682170543,
         0.8914728682170543
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.10852713178294573,
         0.10852713178294573
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.10852713178294573,
         0.10852713178294573
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "89",
         "p1": "89.1",
         "count": "115"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "11",
         "p1": "10.9",
         "count": "14"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "11",
         "p1": "10.9",
         "count": "14"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "gemma4:26b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         127,
         127
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.9844961240310077,
         0.9844961240310077
        ],
        "abstain": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "98",
         "p1": "98.4",
         "count": "127"
        },
        "abstain": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         101,
         104
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         28,
         25
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         28,
         25
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.7829457364341085,
         0.8062015503875969
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.21705426356589147,
         0.1937984496124031
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.21705426356589147,
         0.1937984496124031
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "78〜81",
         "p1": "78.3〜80.6",
         "count": "101〜104"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "19〜22",
         "p1": "19.4〜21.7",
         "count": "25〜28"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "19〜22",
         "p1": "19.4〜21.7",
         "count": "25〜28"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         128,
         127
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         2
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         2
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9922480620155039,
         0.9844961240310077
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.007751937984496124,
         0.015503875968992248
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.007751937984496124,
         0.015503875968992248
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "98〜99",
         "p1": "98.4〜99.2",
         "count": "127〜128"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1〜2",
         "p1": "0.8〜1.6",
         "count": "1〜2"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1〜2",
         "p1": "0.8〜1.6",
         "count": "1〜2"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         126,
         125
        ],
        "abstain": [
         3,
         4
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.9767441860465116,
         0.9689922480620154
        ],
        "abstain": [
         0.023255813953488372,
         0.031007751937984496
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "97〜98",
         "p1": "96.9〜97.7",
         "count": "125〜126"
        },
        "abstain": {
         "p0": "2〜3",
         "p1": "2.3〜3.1",
         "count": "3〜4"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         119,
         118
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         10,
         11
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         10,
         11
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9224806201550387,
         0.9147286821705426
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.07751937984496124,
         0.08527131782945736
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.07751937984496124,
         0.08527131782945736
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "91〜92",
         "p1": "91.5〜92.2",
         "count": "118〜119"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "8〜9",
         "p1": "7.8〜8.5",
         "count": "10〜11"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "8〜9",
         "p1": "7.8〜8.5",
         "count": "10〜11"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         126,
         126
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.9767441860465116,
         0.9767441860465116
        ],
        "abstain": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.007751937984496124,
         0.007751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "98",
         "p1": "97.7",
         "count": "126"
        },
        "abstain": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         119,
         119
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         9,
         9
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         9,
         9
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9224806201550387,
         0.9224806201550387
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.06976744186046512,
         0.06976744186046512
        ],
        "unresolved": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "answered": [
         0.06976744186046512,
         0.06976744186046512
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "92",
         "p1": "92.2",
         "count": "119"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "7",
         "p1": "7.0",
         "count": "9"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "answered": {
         "p0": "7",
         "p1": "7.0",
         "count": "9"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "gpt-oss:20b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         127,
         127
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         2
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         2
        ]
       },
       "rates": {
        "correct": [
         0.9844961240310077,
         0.9844961240310077
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.015503875968992248,
         0.015503875968992248
        ]
       },
       "disp": {
        "correct": {
         "p0": "98",
         "p1": "98.4",
         "count": "127"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         2,
         1
        ],
        "abstain": [
         25,
         23
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         102,
         105
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         102,
         105
        ]
       },
       "rates": {
        "correct": [
         0.015503875968992248,
         0.007751937984496124
        ],
        "abstain": [
         0.1937984496124031,
         0.17829457364341086
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.7906976744186046,
         0.813953488372093
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.7906976744186046,
         0.813953488372093
        ]
       },
       "disp": {
        "correct": {
         "p0": "1〜2",
         "p1": "0.8〜1.6",
         "count": "1〜2"
        },
        "abstain": {
         "p0": "18〜19",
         "p1": "17.8〜19.4",
         "count": "23〜25"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "79〜81",
         "p1": "79.1〜81.4",
         "count": "102〜105"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "79〜81",
         "p1": "79.1〜81.4",
         "count": "102〜105"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         3,
         3
        ],
        "abstain": [
         17,
         17
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         109,
         109
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         109,
         109
        ]
       },
       "rates": {
        "correct": [
         0.023255813953488372,
         0.023255813953488372
        ],
        "abstain": [
         0.13178294573643412,
         0.13178294573643412
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.8449612403100775,
         0.8449612403100775
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.8449612403100775,
         0.8449612403100775
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "2.3",
         "count": "3"
        },
        "abstain": {
         "p0": "13",
         "p1": "13.2",
         "count": "17"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "84",
         "p1": "84.5",
         "count": "109"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "84",
         "p1": "84.5",
         "count": "109"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         125,
         125
        ],
        "abstain": [
         1,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9689922480620154,
         0.9689922480620154
        ],
        "abstain": [
         0.007751937984496124,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023255813953488372,
         0.031007751937984496
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023255813953488372,
         0.031007751937984496
        ]
       },
       "disp": {
        "correct": {
         "p0": "97",
         "p1": "96.9",
         "count": "125"
        },
        "abstain": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2〜3",
         "p1": "2.3〜3.1",
         "count": "3〜4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2〜3",
         "p1": "2.3〜3.1",
         "count": "3〜4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         98,
         99
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         30,
         29
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         30,
         29
        ]
       },
       "rates": {
        "correct": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "abstain": [
         0.7596899224806202,
         0.7674418604651163
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.23255813953488372,
         0.2248062015503876
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.23255813953488372,
         0.2248062015503876
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "abstain": {
         "p0": "76〜77",
         "p1": "76.0〜76.7",
         "count": "98〜99"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "22〜23",
         "p1": "22.5〜23.3",
         "count": "29〜30"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "22〜23",
         "p1": "22.5〜23.3",
         "count": "29〜30"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         125,
         126
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         3
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9689922480620154,
         0.9767441860465116
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.031007751937984496,
         0.023255813953488372
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.031007751937984496,
         0.023255813953488372
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "97〜98",
         "p1": "96.9〜97.7",
         "count": "125〜126"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2〜3",
         "p1": "2.3〜3.1",
         "count": "3〜4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2〜3",
         "p1": "2.3〜3.1",
         "count": "3〜4"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         126,
         125
        ],
        "abstain": [
         1,
         1
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         3
        ]
       },
       "rates": {
        "correct": [
         0.9767441860465116,
         0.9689922480620154
        ],
        "abstain": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.015503875968992248,
         0.023255813953488372
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.015503875968992248,
         0.023255813953488372
        ]
       },
       "disp": {
        "correct": {
         "p0": "97〜98",
         "p1": "96.9〜97.7",
         "count": "125〜126"
        },
        "abstain": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         95,
         96
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         33,
         32
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         33,
         32
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.7364341085271318,
         0.7441860465116279
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.2558139534883721,
         0.24806201550387597
        ],
        "unresolved": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "answered": [
         0.2558139534883721,
         0.24806201550387597
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "74",
         "p1": "73.6〜74.4",
         "count": "95〜96"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "25〜26",
         "p1": "24.8〜25.6",
         "count": "32〜33"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "answered": {
         "p0": "25〜26",
         "p1": "24.8〜25.6",
         "count": "32〜33"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         128,
         128
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9922480620155039,
         0.9922480620155039
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.007751937984496124,
         0.007751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "99.2",
         "count": "128"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        }
       }
      }
     }
    },
    "gpt-oss:120b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         126,
         124
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         5
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         5
        ]
       },
       "rates": {
        "correct": [
         0.9767441860465116,
         0.9612403100775194
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023255813953488372,
         0.03875968992248062
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023255813953488372,
         0.03875968992248062
        ]
       },
       "disp": {
        "correct": {
         "p0": "96〜98",
         "p1": "96.1〜97.7",
         "count": "124〜126"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2〜4",
         "p1": "2.3〜3.9",
         "count": "3〜5"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2〜4",
         "p1": "2.3〜3.9",
         "count": "3〜5"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         2,
         2
        ],
        "abstain": [
         32,
         33
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         95,
         94
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         95,
         94
        ]
       },
       "rates": {
        "correct": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "abstain": [
         0.24806201550387597,
         0.2558139534883721
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.7364341085271318,
         0.7286821705426356
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.7364341085271318,
         0.7286821705426356
        ]
       },
       "disp": {
        "correct": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "abstain": {
         "p0": "25〜26",
         "p1": "24.8〜25.6",
         "count": "32〜33"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "73〜74",
         "p1": "72.9〜73.6",
         "count": "94〜95"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "73〜74",
         "p1": "72.9〜73.6",
         "count": "94〜95"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         2,
         1
        ],
        "abstain": [
         41,
         39
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         86,
         89
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         86,
         89
        ]
       },
       "rates": {
        "correct": [
         0.015503875968992248,
         0.007751937984496124
        ],
        "abstain": [
         0.3178294573643411,
         0.3023255813953488
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.6666666666666666,
         0.689922480620155
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.6666666666666666,
         0.689922480620155
        ]
       },
       "disp": {
        "correct": {
         "p0": "1〜2",
         "p1": "0.8〜1.6",
         "count": "1〜2"
        },
        "abstain": {
         "p0": "30〜32",
         "p1": "30.2〜31.8",
         "count": "39〜41"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "67〜69",
         "p1": "66.7〜69.0",
         "count": "86〜89"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "67〜69",
         "p1": "66.7〜69.0",
         "count": "86〜89"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         125,
         124
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         2,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         2,
         3
        ]
       },
       "rates": {
        "correct": [
         0.9689922480620154,
         0.9612403100775194
        ],
        "abstain": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.015503875968992248,
         0.023255813953488372
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.015503875968992248,
         0.023255813953488372
        ]
       },
       "disp": {
        "correct": {
         "p0": "96〜97",
         "p1": "96.1〜96.9",
         "count": "124〜125"
        },
        "abstain": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         120,
         120
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         9,
         9
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         9,
         9
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9302325581395349,
         0.9302325581395349
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.06976744186046512,
         0.06976744186046512
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.06976744186046512,
         0.06976744186046512
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "93",
         "p1": "93.0",
         "count": "120"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "7",
         "p1": "7.0",
         "count": "9"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "7",
         "p1": "7.0",
         "count": "9"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         128,
         128
        ],
        "abstain": [
         1,
         1
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.9922480620155039,
         0.9922480620155039
        ],
        "abstain": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "99",
         "p1": "99.2",
         "count": "128"
        },
        "abstain": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         117,
         117
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         12,
         11
        ],
        "unresolved": [
         0,
         1
        ],
        "answered": [
         12,
         11
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9069767441860465,
         0.9069767441860465
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.09302325581395349,
         0.08527131782945736
        ],
        "unresolved": [
         0.0,
         0.007751937984496124
        ],
        "answered": [
         0.09302325581395349,
         0.08527131782945736
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "91",
         "p1": "90.7",
         "count": "117"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "9",
         "p1": "8.5〜9.3",
         "count": "11〜12"
        },
        "unresolved": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "answered": {
         "p0": "9",
         "p1": "8.5〜9.3",
         "count": "11〜12"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         128
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         0.9922480620155039
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.007751937984496124
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.007751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99〜100",
         "p1": "99.2〜100.0",
         "count": "128〜129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        }
       }
      }
     }
    },
    "deepseek-r1:8b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         104,
         108
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         11,
         12
        ],
        "unresolved": [
         12,
         7
        ],
        "answered": [
         11,
         12
        ]
       },
       "rates": {
        "correct": [
         0.8062015503875969,
         0.8372093023255814
        ],
        "abstain": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.08527131782945736,
         0.09302325581395349
        ],
        "unresolved": [
         0.09302325581395349,
         0.05426356589147287
        ],
        "answered": [
         0.08527131782945736,
         0.09302325581395349
        ]
       },
       "disp": {
        "correct": {
         "p0": "81〜84",
         "p1": "80.6〜83.7",
         "count": "104〜108"
        },
        "abstain": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "9",
         "p1": "8.5〜9.3",
         "count": "11〜12"
        },
        "unresolved": {
         "p0": "5〜9",
         "p1": "5.4〜9.3",
         "count": "7〜12"
        },
        "answered": {
         "p0": "9",
         "p1": "8.5〜9.3",
         "count": "11〜12"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         1
        ],
        "abstain": [
         52,
         50
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         49,
         48
        ],
        "unresolved": [
         28,
         30
        ],
        "answered": [
         49,
         48
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.007751937984496124
        ],
        "abstain": [
         0.40310077519379844,
         0.3875968992248062
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.3798449612403101,
         0.37209302325581395
        ],
        "unresolved": [
         0.21705426356589147,
         0.23255813953488372
        ],
        "answered": [
         0.3798449612403101,
         0.37209302325581395
        ]
       },
       "disp": {
        "correct": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "abstain": {
         "p0": "39〜40",
         "p1": "38.8〜40.3",
         "count": "50〜52"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "37〜38",
         "p1": "37.2〜38.0",
         "count": "48〜49"
        },
        "unresolved": {
         "p0": "22〜23",
         "p1": "21.7〜23.3",
         "count": "28〜30"
        },
        "answered": {
         "p0": "37〜38",
         "p1": "37.2〜38.0",
         "count": "48〜49"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         112,
         102
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         8,
         13
        ],
        "unresolved": [
         9,
         14
        ],
        "answered": [
         8,
         13
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.8682170542635659,
         0.7906976744186046
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.06201550387596899,
         0.10077519379844961
        ],
        "unresolved": [
         0.06976744186046512,
         0.10852713178294573
        ],
        "answered": [
         0.06201550387596899,
         0.10077519379844961
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "79〜87",
         "p1": "79.1〜86.8",
         "count": "102〜112"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "6〜10",
         "p1": "6.2〜10.1",
         "count": "8〜13"
        },
        "unresolved": {
         "p0": "7〜11",
         "p1": "7.0〜10.9",
         "count": "9〜14"
        },
        "answered": {
         "p0": "6〜10",
         "p1": "6.2〜10.1",
         "count": "8〜13"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         105,
         99
        ],
        "abstain": [
         11,
         17
        ],
        "hedged": [
         1,
         0
        ],
        "other": [
         5,
         9
        ],
        "unresolved": [
         7,
         4
        ],
        "answered": [
         6,
         9
        ]
       },
       "rates": {
        "correct": [
         0.813953488372093,
         0.7674418604651163
        ],
        "abstain": [
         0.08527131782945736,
         0.13178294573643412
        ],
        "hedged": [
         0.007751937984496124,
         0.0
        ],
        "other": [
         0.03875968992248062,
         0.06976744186046512
        ],
        "unresolved": [
         0.05426356589147287,
         0.031007751937984496
        ],
        "answered": [
         0.046511627906976744,
         0.06976744186046512
        ]
       },
       "disp": {
        "correct": {
         "p0": "77〜81",
         "p1": "76.7〜81.4",
         "count": "99〜105"
        },
        "abstain": {
         "p0": "9〜13",
         "p1": "8.5〜13.2",
         "count": "11〜17"
        },
        "hedged": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "other": {
         "p0": "4〜7",
         "p1": "3.9〜7.0",
         "count": "5〜9"
        },
        "unresolved": {
         "p0": "3〜5",
         "p1": "3.1〜5.4",
         "count": "4〜7"
        },
        "answered": {
         "p0": "5〜7",
         "p1": "4.7〜7.0",
         "count": "6〜9"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         1
        ],
        "abstain": [
         104,
         101
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         16,
         13
        ],
        "unresolved": [
         9,
         14
        ],
        "answered": [
         16,
         13
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.007751937984496124
        ],
        "abstain": [
         0.8062015503875969,
         0.7829457364341085
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.12403100775193798,
         0.10077519379844961
        ],
        "unresolved": [
         0.06976744186046512,
         0.10852713178294573
        ],
        "answered": [
         0.12403100775193798,
         0.10077519379844961
        ]
       },
       "disp": {
        "correct": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "abstain": {
         "p0": "78〜81",
         "p1": "78.3〜80.6",
         "count": "101〜104"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "10〜12",
         "p1": "10.1〜12.4",
         "count": "13〜16"
        },
        "unresolved": {
         "p0": "7〜11",
         "p1": "7.0〜10.9",
         "count": "9〜14"
        },
        "answered": {
         "p0": "10〜12",
         "p1": "10.1〜12.4",
         "count": "13〜16"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         127,
         125
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         2
        ],
        "unresolved": [
         2,
         2
        ],
        "answered": [
         0,
         2
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9844961240310077,
         0.9689922480620154
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.015503875968992248
        ],
        "unresolved": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "answered": [
         0.0,
         0.015503875968992248
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "97〜98",
         "p1": "96.9〜98.4",
         "count": "125〜127"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0〜2",
         "p1": "0.0〜1.6",
         "count": "0〜2"
        },
        "unresolved": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "answered": {
         "p0": "0〜2",
         "p1": "0.0〜1.6",
         "count": "0〜2"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         107,
         109
        ],
        "abstain": [
         9,
         8
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         6,
         7
        ],
        "unresolved": [
         7,
         5
        ],
        "answered": [
         6,
         7
        ]
       },
       "rates": {
        "correct": [
         0.8294573643410853,
         0.8449612403100775
        ],
        "abstain": [
         0.06976744186046512,
         0.06201550387596899
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.046511627906976744,
         0.05426356589147287
        ],
        "unresolved": [
         0.05426356589147287,
         0.03875968992248062
        ],
        "answered": [
         0.046511627906976744,
         0.05426356589147287
        ]
       },
       "disp": {
        "correct": {
         "p0": "83〜84",
         "p1": "82.9〜84.5",
         "count": "107〜109"
        },
        "abstain": {
         "p0": "6〜7",
         "p1": "6.2〜7.0",
         "count": "8〜9"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5",
         "p1": "4.7〜5.4",
         "count": "6〜7"
        },
        "unresolved": {
         "p0": "4〜5",
         "p1": "3.9〜5.4",
         "count": "5〜7"
        },
        "answered": {
         "p0": "5",
         "p1": "4.7〜5.4",
         "count": "6〜7"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         1
        ],
        "abstain": [
         101,
         104
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         12,
         10
        ],
        "unresolved": [
         16,
         14
        ],
        "answered": [
         12,
         10
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.007751937984496124
        ],
        "abstain": [
         0.7829457364341085,
         0.8062015503875969
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.09302325581395349,
         0.07751937984496124
        ],
        "unresolved": [
         0.12403100775193798,
         0.10852713178294573
        ],
        "answered": [
         0.09302325581395349,
         0.07751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "abstain": {
         "p0": "78〜81",
         "p1": "78.3〜80.6",
         "count": "101〜104"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "8〜9",
         "p1": "7.8〜9.3",
         "count": "10〜12"
        },
        "unresolved": {
         "p0": "11〜12",
         "p1": "10.9〜12.4",
         "count": "14〜16"
        },
        "answered": {
         "p0": "8〜9",
         "p1": "7.8〜9.3",
         "count": "10〜12"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         125,
         127
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         3,
         1
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9689922480620154,
         0.9844961240310077
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "unresolved": [
         0.023255813953488372,
         0.007751937984496124
        ],
        "answered": [
         0.007751937984496124,
         0.007751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "97〜98",
         "p1": "96.9〜98.4",
         "count": "125〜127"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "unresolved": {
         "p0": "1〜2",
         "p1": "0.8〜2.3",
         "count": "1〜3"
        },
        "answered": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        }
       }
      }
     }
    },
    "deepseek-r1:14b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         123,
         121
        ],
        "abstain": [
         0,
         1
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         5,
         6
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         5,
         6
        ]
       },
       "rates": {
        "correct": [
         0.9534883720930233,
         0.937984496124031
        ],
        "abstain": [
         0.0,
         0.007751937984496124
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.03875968992248062,
         0.046511627906976744
        ],
        "unresolved": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "answered": [
         0.03875968992248062,
         0.046511627906976744
        ]
       },
       "disp": {
        "correct": {
         "p0": "94〜95",
         "p1": "93.8〜95.3",
         "count": "121〜123"
        },
        "abstain": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4〜5",
         "p1": "3.9〜4.7",
         "count": "5〜6"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "answered": {
         "p0": "4〜5",
         "p1": "3.9〜4.7",
         "count": "5〜6"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         1,
         0
        ],
        "abstain": [
         59,
         61
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         65,
         64
        ],
        "unresolved": [
         4,
         4
        ],
        "answered": [
         65,
         64
        ]
       },
       "rates": {
        "correct": [
         0.007751937984496124,
         0.0
        ],
        "abstain": [
         0.4573643410852713,
         0.4728682170542636
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.5038759689922481,
         0.49612403100775193
        ],
        "unresolved": [
         0.031007751937984496,
         0.031007751937984496
        ],
        "answered": [
         0.5038759689922481,
         0.49612403100775193
        ]
       },
       "disp": {
        "correct": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "abstain": {
         "p0": "46〜47",
         "p1": "45.7〜47.3",
         "count": "59〜61"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "50",
         "p1": "49.6〜50.4",
         "count": "64〜65"
        },
        "unresolved": {
         "p0": "3",
         "p1": "3.1",
         "count": "4"
        },
        "answered": {
         "p0": "50",
         "p1": "49.6〜50.4",
         "count": "64〜65"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         117,
         117
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         12,
         12
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         12,
         12
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9069767441860465,
         0.9069767441860465
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.09302325581395349,
         0.09302325581395349
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.09302325581395349,
         0.09302325581395349
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "91",
         "p1": "90.7",
         "count": "117"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "9",
         "p1": "9.3",
         "count": "12"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "9",
         "p1": "9.3",
         "count": "12"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         121,
         122
        ],
        "abstain": [
         5,
         5
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         2
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         2
        ]
       },
       "rates": {
        "correct": [
         0.937984496124031,
         0.9457364341085271
        ],
        "abstain": [
         0.03875968992248062,
         0.03875968992248062
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023255813953488372,
         0.015503875968992248
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023255813953488372,
         0.015503875968992248
        ]
       },
       "disp": {
        "correct": {
         "p0": "94〜95",
         "p1": "93.8〜94.6",
         "count": "121〜122"
        },
        "abstain": {
         "p0": "4",
         "p1": "3.9",
         "count": "5"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         116,
         117
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         13,
         12
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         13,
         12
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.8992248062015504,
         0.9069767441860465
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.10077519379844961,
         0.09302325581395349
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.10077519379844961,
         0.09302325581395349
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "90〜91",
         "p1": "89.9〜90.7",
         "count": "116〜117"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "9〜10",
         "p1": "9.3〜10.1",
         "count": "12〜13"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "9〜10",
         "p1": "9.3〜10.1",
         "count": "12〜13"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         128,
         128
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9922480620155039,
         0.9922480620155039
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.007751937984496124,
         0.007751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "99.2",
         "count": "128"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         120,
         121
        ],
        "abstain": [
         5,
         4
        ],
        "hedged": [
         0,
         1
        ],
        "other": [
         4,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9302325581395349,
         0.937984496124031
        ],
        "abstain": [
         0.03875968992248062,
         0.031007751937984496
        ],
        "hedged": [
         0.0,
         0.007751937984496124
        ],
        "other": [
         0.031007751937984496,
         0.023255813953488372
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.031007751937984496,
         0.031007751937984496
        ]
       },
       "disp": {
        "correct": {
         "p0": "93〜94",
         "p1": "93.0〜93.8",
         "count": "120〜121"
        },
        "abstain": {
         "p0": "3〜4",
         "p1": "3.1〜3.9",
         "count": "4〜5"
        },
        "hedged": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "other": {
         "p0": "2〜3",
         "p1": "2.3〜3.1",
         "count": "3〜4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3",
         "p1": "3.1",
         "count": "4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         114,
         110
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         15,
         19
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         15,
         19
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.8837209302325582,
         0.8527131782945736
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.11627906976744186,
         0.14728682170542637
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.11627906976744186,
         0.14728682170542637
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "85〜88",
         "p1": "85.3〜88.4",
         "count": "110〜114"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "12〜15",
         "p1": "11.6〜14.7",
         "count": "15〜19"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "12〜15",
         "p1": "11.6〜14.7",
         "count": "15〜19"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         128,
         128
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         1,
         1
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         1,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9922480620155039,
         0.9922480620155039
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.007751937984496124,
         0.007751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "99",
         "p1": "99.2",
         "count": "128"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        }
       }
      }
     }
    },
    "llama3.1:8b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         121,
         122
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         8,
         7
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         8,
         7
        ]
       },
       "rates": {
        "correct": [
         0.937984496124031,
         0.9457364341085271
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.06201550387596899,
         0.05426356589147287
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.06201550387596899,
         0.05426356589147287
        ]
       },
       "disp": {
        "correct": {
         "p0": "94〜95",
         "p1": "93.8〜94.6",
         "count": "121〜122"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5〜6",
         "p1": "5.4〜6.2",
         "count": "7〜8"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "5〜6",
         "p1": "5.4〜6.2",
         "count": "7〜8"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         23,
         23
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         102,
         103
        ],
        "unresolved": [
         4,
         3
        ],
        "answered": [
         102,
         103
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.17829457364341086,
         0.17829457364341086
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.7906976744186046,
         0.7984496124031008
        ],
        "unresolved": [
         0.031007751937984496,
         0.023255813953488372
        ],
        "answered": [
         0.7906976744186046,
         0.7984496124031008
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "18",
         "p1": "17.8",
         "count": "23"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "79〜80",
         "p1": "79.1〜79.8",
         "count": "102〜103"
        },
        "unresolved": {
         "p0": "2〜3",
         "p1": "2.3〜3.1",
         "count": "3〜4"
        },
        "answered": {
         "p0": "79〜80",
         "p1": "79.1〜79.8",
         "count": "102〜103"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         71,
         68
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         56,
         57
        ],
        "unresolved": [
         2,
         4
        ],
        "answered": [
         56,
         57
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.5503875968992248,
         0.5271317829457365
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.43410852713178294,
         0.4418604651162791
        ],
        "unresolved": [
         0.015503875968992248,
         0.031007751937984496
        ],
        "answered": [
         0.43410852713178294,
         0.4418604651162791
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "53〜55",
         "p1": "52.7〜55.0",
         "count": "68〜71"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "43〜44",
         "p1": "43.4〜44.2",
         "count": "56〜57"
        },
        "unresolved": {
         "p0": "2〜3",
         "p1": "1.6〜3.1",
         "count": "2〜4"
        },
        "answered": {
         "p0": "43〜44",
         "p1": "43.4〜44.2",
         "count": "56〜57"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         107,
         106
        ],
        "abstain": [
         5,
         5
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         13,
         12
        ],
        "unresolved": [
         4,
         6
        ],
        "answered": [
         13,
         12
        ]
       },
       "rates": {
        "correct": [
         0.8294573643410853,
         0.8217054263565892
        ],
        "abstain": [
         0.03875968992248062,
         0.03875968992248062
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.10077519379844961,
         0.09302325581395349
        ],
        "unresolved": [
         0.031007751937984496,
         0.046511627906976744
        ],
        "answered": [
         0.10077519379844961,
         0.09302325581395349
        ]
       },
       "disp": {
        "correct": {
         "p0": "82〜83",
         "p1": "82.2〜82.9",
         "count": "106〜107"
        },
        "abstain": {
         "p0": "4",
         "p1": "3.9",
         "count": "5"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "9〜10",
         "p1": "9.3〜10.1",
         "count": "12〜13"
        },
        "unresolved": {
         "p0": "3〜5",
         "p1": "3.1〜4.7",
         "count": "4〜6"
        },
        "answered": {
         "p0": "9〜10",
         "p1": "9.3〜10.1",
         "count": "12〜13"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         91,
         90
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         19,
         19
        ],
        "unresolved": [
         19,
         20
        ],
        "answered": [
         19,
         19
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.7054263565891473,
         0.6976744186046512
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.14728682170542637,
         0.14728682170542637
        ],
        "unresolved": [
         0.14728682170542637,
         0.15503875968992248
        ],
        "answered": [
         0.14728682170542637,
         0.14728682170542637
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "70〜71",
         "p1": "69.8〜70.5",
         "count": "90〜91"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "15",
         "p1": "14.7",
         "count": "19"
        },
        "unresolved": {
         "p0": "15〜16",
         "p1": "14.7〜15.5",
         "count": "19〜20"
        },
        "answered": {
         "p0": "15",
         "p1": "14.7",
         "count": "19"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         126,
         126
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         1
        ],
        "unresolved": [
         3,
         2
        ],
        "answered": [
         0,
         1
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9767441860465116,
         0.9767441860465116
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.007751937984496124
        ],
        "unresolved": [
         0.023255813953488372,
         0.015503875968992248
        ],
        "answered": [
         0.0,
         0.007751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "98",
         "p1": "97.7",
         "count": "126"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        },
        "unresolved": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        },
        "answered": {
         "p0": "0〜1",
         "p1": "0.0〜0.8",
         "count": "0〜1"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         113,
         112
        ],
        "abstain": [
         2,
         2
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         13,
         14
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         13,
         14
        ]
       },
       "rates": {
        "correct": [
         0.875968992248062,
         0.8682170542635659
        ],
        "abstain": [
         0.015503875968992248,
         0.015503875968992248
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.10077519379844961,
         0.10852713178294573
        ],
        "unresolved": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "answered": [
         0.10077519379844961,
         0.10852713178294573
        ]
       },
       "disp": {
        "correct": {
         "p0": "87〜88",
         "p1": "86.8〜87.6",
         "count": "112〜113"
        },
        "abstain": {
         "p0": "2",
         "p1": "1.6",
         "count": "2"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "10〜11",
         "p1": "10.1〜10.9",
         "count": "13〜14"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "answered": {
         "p0": "10〜11",
         "p1": "10.1〜10.9",
         "count": "13〜14"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         43,
         45
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         83,
         78
        ],
        "unresolved": [
         2,
         5
        ],
        "answered": [
         83,
         78
        ]
       },
       "rates": {
        "correct": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "abstain": [
         0.3333333333333333,
         0.3488372093023256
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.6434108527131783,
         0.6046511627906976
        ],
        "unresolved": [
         0.015503875968992248,
         0.03875968992248062
        ],
        "answered": [
         0.6434108527131783,
         0.6046511627906976
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "abstain": {
         "p0": "33〜35",
         "p1": "33.3〜34.9",
         "count": "43〜45"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "60〜64",
         "p1": "60.5〜64.3",
         "count": "78〜83"
        },
        "unresolved": {
         "p0": "2〜4",
         "p1": "1.6〜3.9",
         "count": "2〜5"
        },
        "answered": {
         "p0": "60〜64",
         "p1": "60.5〜64.3",
         "count": "78〜83"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         91,
         93
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         35,
         33
        ],
        "unresolved": [
         3,
         3
        ],
        "answered": [
         35,
         33
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.7054263565891473,
         0.7209302325581395
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.2713178294573643,
         0.2558139534883721
        ],
        "unresolved": [
         0.023255813953488372,
         0.023255813953488372
        ],
        "answered": [
         0.2713178294573643,
         0.2558139534883721
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "71〜72",
         "p1": "70.5〜72.1",
         "count": "91〜93"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "26〜27",
         "p1": "25.6〜27.1",
         "count": "33〜35"
        },
        "unresolved": {
         "p0": "2",
         "p1": "2.3",
         "count": "3"
        },
        "answered": {
         "p0": "26〜27",
         "p1": "25.6〜27.1",
         "count": "33〜35"
        }
       }
      }
     }
    },
    "mistral-small3.2:24b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         124,
         124
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         5,
         5
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         5,
         5
        ]
       },
       "rates": {
        "correct": [
         0.9612403100775194,
         0.9612403100775194
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.03875968992248062,
         0.03875968992248062
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.03875968992248062,
         0.03875968992248062
        ]
       },
       "disp": {
        "correct": {
         "p0": "96",
         "p1": "96.1",
         "count": "124"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4",
         "p1": "3.9",
         "count": "5"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "4",
         "p1": "3.9",
         "count": "5"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         59,
         57
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         70,
         72
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         70,
         72
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.4573643410852713,
         0.4418604651162791
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.5426356589147286,
         0.5581395348837209
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.5426356589147286,
         0.5581395348837209
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "44〜46",
         "p1": "44.2〜45.7",
         "count": "57〜59"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "54〜56",
         "p1": "54.3〜55.8",
         "count": "70〜72"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "54〜56",
         "p1": "54.3〜55.8",
         "count": "70〜72"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         118,
         118
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         10,
         10
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         10,
         10
        ]
       },
       "rates": {
        "correct": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "abstain": [
         0.9147286821705426,
         0.9147286821705426
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.07751937984496124,
         0.07751937984496124
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.07751937984496124,
         0.07751937984496124
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "abstain": {
         "p0": "91",
         "p1": "91.5",
         "count": "118"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "8",
         "p1": "7.8",
         "count": "10"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "8",
         "p1": "7.8",
         "count": "10"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         122,
         122
        ],
        "abstain": [
         4,
         4
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         3,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         3
        ]
       },
       "rates": {
        "correct": [
         0.9457364341085271,
         0.9457364341085271
        ],
        "abstain": [
         0.031007751937984496,
         0.031007751937984496
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.023255813953488372,
         0.023255813953488372
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023255813953488372,
         0.023255813953488372
        ]
       },
       "disp": {
        "correct": {
         "p0": "95",
         "p1": "94.6",
         "count": "122"
        },
        "abstain": {
         "p0": "3",
         "p1": "3.1",
         "count": "4"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "2",
         "p1": "2.3",
         "count": "3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2",
         "p1": "2.3",
         "count": "3"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         115,
         115
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         14,
         14
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         14,
         14
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.8914728682170543,
         0.8914728682170543
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.10852713178294573,
         0.10852713178294573
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.10852713178294573,
         0.10852713178294573
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "89",
         "p1": "89.1",
         "count": "115"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "11",
         "p1": "10.9",
         "count": "14"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "11",
         "p1": "10.9",
         "count": "14"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         124,
         124
        ],
        "abstain": [
         1,
         1
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         4
        ]
       },
       "rates": {
        "correct": [
         0.9612403100775194,
         0.9612403100775194
        ],
        "abstain": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.031007751937984496,
         0.031007751937984496
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.031007751937984496,
         0.031007751937984496
        ]
       },
       "disp": {
        "correct": {
         "p0": "96",
         "p1": "96.1",
         "count": "124"
        },
        "abstain": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3",
         "p1": "3.1",
         "count": "4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3",
         "p1": "3.1",
         "count": "4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         110,
         110
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         18,
         18
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         18,
         18
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.8527131782945736,
         0.8527131782945736
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.13953488372093023,
         0.13953488372093023
        ],
        "unresolved": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "answered": [
         0.13953488372093023,
         0.13953488372093023
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "85",
         "p1": "85.3",
         "count": "110"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "14",
         "p1": "14.0",
         "count": "18"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "answered": {
         "p0": "14",
         "p1": "14.0",
         "count": "18"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    },
    "phi4:14b": {
     "plain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         124,
         124
        ],
        "abstain": [
         0,
         0
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         5,
         5
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         5,
         5
        ]
       },
       "rates": {
        "correct": [
         0.9612403100775194,
         0.9612403100775194
        ],
        "abstain": [
         0.0,
         0.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.03875968992248062,
         0.03875968992248062
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.03875968992248062,
         0.03875968992248062
        ]
       },
       "disp": {
        "correct": {
         "p0": "96",
         "p1": "96.1",
         "count": "124"
        },
        "abstain": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "4",
         "p1": "3.9",
         "count": "5"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "4",
         "p1": "3.9",
         "count": "5"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         1,
         1
        ],
        "abstain": [
         81,
         83
        ],
        "hedged": [
         1,
         1
        ],
        "other": [
         46,
         44
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         47,
         45
        ]
       },
       "rates": {
        "correct": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "abstain": [
         0.627906976744186,
         0.6434108527131783
        ],
        "hedged": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "other": [
         0.35658914728682173,
         0.34108527131782945
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.3643410852713178,
         0.3488372093023256
        ]
       },
       "disp": {
        "correct": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "abstain": {
         "p0": "63〜64",
         "p1": "62.8〜64.3",
         "count": "81〜83"
        },
        "hedged": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "other": {
         "p0": "34〜36",
         "p1": "34.1〜35.7",
         "count": "44〜46"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "35〜36",
         "p1": "34.9〜36.4",
         "count": "45〜47"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         125,
         125
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         4,
         4
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         4,
         4
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9689922480620154,
         0.9689922480620154
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.031007751937984496,
         0.031007751937984496
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.031007751937984496,
         0.031007751937984496
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "97",
         "p1": "96.9",
         "count": "125"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "3",
         "p1": "3.1",
         "count": "4"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "3",
         "p1": "3.1",
         "count": "4"
        }
       }
      }
     },
     "abstain": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         113,
         112
        ],
        "abstain": [
         13,
         13
        ],
        "hedged": [
         1,
         1
        ],
        "other": [
         2,
         3
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         3,
         4
        ]
       },
       "rates": {
        "correct": [
         0.875968992248062,
         0.8682170542635659
        ],
        "abstain": [
         0.10077519379844961,
         0.10077519379844961
        ],
        "hedged": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "other": [
         0.015503875968992248,
         0.023255813953488372
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.023255813953488372,
         0.031007751937984496
        ]
       },
       "disp": {
        "correct": {
         "p0": "87〜88",
         "p1": "86.8〜87.6",
         "count": "112〜113"
        },
        "abstain": {
         "p0": "10",
         "p1": "10.1",
         "count": "13"
        },
        "hedged": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "other": {
         "p0": "2",
         "p1": "1.6〜2.3",
         "count": "2〜3"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "2〜3",
         "p1": "2.3〜3.1",
         "count": "3〜4"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         122,
         122
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         7,
         7
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         7,
         7
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9457364341085271,
         0.9457364341085271
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.05426356589147287,
         0.05426356589147287
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.05426356589147287,
         0.05426356589147287
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "95",
         "p1": "94.6",
         "count": "122"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5",
         "p1": "5.4",
         "count": "7"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "5",
         "p1": "5.4",
         "count": "7"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     },
     "quote": {
      "answerable": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         115,
         114
        ],
        "abstain": [
         7,
         7
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         6,
         7
        ],
        "unresolved": [
         1,
         1
        ],
        "answered": [
         6,
         7
        ]
       },
       "rates": {
        "correct": [
         0.8914728682170543,
         0.8837209302325582
        ],
        "abstain": [
         0.05426356589147287,
         0.05426356589147287
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.046511627906976744,
         0.05426356589147287
        ],
        "unresolved": [
         0.007751937984496124,
         0.007751937984496124
        ],
        "answered": [
         0.046511627906976744,
         0.05426356589147287
        ]
       },
       "disp": {
        "correct": {
         "p0": "88〜89",
         "p1": "88.4〜89.1",
         "count": "114〜115"
        },
        "abstain": {
         "p0": "5",
         "p1": "5.4",
         "count": "7"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5",
         "p1": "4.7〜5.4",
         "count": "6〜7"
        },
        "unresolved": {
         "p0": "1",
         "p1": "0.8",
         "count": "1"
        },
        "answered": {
         "p0": "5",
         "p1": "4.7〜5.4",
         "count": "6〜7"
        }
       }
      },
      "near": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         122,
         123
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         7,
         6
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         7,
         6
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         0.9457364341085271,
         0.9534883720930233
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.05426356589147287,
         0.046511627906976744
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.05426356589147287,
         0.046511627906976744
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "95",
         "p1": "94.6〜95.3",
         "count": "122〜123"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "5",
         "p1": "4.7〜5.4",
         "count": "6〜7"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "5",
         "p1": "4.7〜5.4",
         "count": "6〜7"
        }
       }
      },
      "far": {
       "runs": [
        1,
        2
       ],
       "n": [
        129,
        129
       ],
       "counts": {
        "correct": [
         0,
         0
        ],
        "abstain": [
         129,
         129
        ],
        "hedged": [
         0,
         0
        ],
        "other": [
         0,
         0
        ],
        "unresolved": [
         0,
         0
        ],
        "answered": [
         0,
         0
        ]
       },
       "rates": {
        "correct": [
         0.0,
         0.0
        ],
        "abstain": [
         1.0,
         1.0
        ],
        "hedged": [
         0.0,
         0.0
        ],
        "other": [
         0.0,
         0.0
        ],
        "unresolved": [
         0.0,
         0.0
        ],
        "answered": [
         0.0,
         0.0
        ]
       },
       "disp": {
        "correct": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "abstain": {
         "p0": "100",
         "p1": "100.0",
         "count": "129"
        },
        "hedged": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "other": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "unresolved": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        },
        "answered": {
         "p0": "0",
         "p1": "0.0",
         "count": "0"
        }
       }
      }
     }
    }
   },
   "nodoc": {
    "deepseek-r1:14b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       1
      ],
      "abstain": [
       9
      ],
      "hedged": [
       0
      ],
      "other": [
       118
      ],
      "unresolved": [
       1
      ],
      "answered": [
       118
      ]
     },
     "rates": {
      "correct": [
       0.007751937984496124
      ],
      "abstain": [
       0.06976744186046512
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9147286821705426
      ],
      "unresolved": [
       0.007751937984496124
      ],
      "answered": [
       0.9147286821705426
      ]
     },
     "disp": {
      "correct": {
       "p0": "1",
       "p1": "0.8",
       "count": "1"
      },
      "abstain": {
       "p0": "7",
       "p1": "7.0",
       "count": "9"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "91",
       "p1": "91.5",
       "count": "118"
      },
      "unresolved": {
       "p0": "1",
       "p1": "0.8",
       "count": "1"
      },
      "answered": {
       "p0": "91",
       "p1": "91.5",
       "count": "118"
      }
     }
    },
    "deepseek-r1:8b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       0
      ],
      "abstain": [
       45
      ],
      "hedged": [
       0
      ],
      "other": [
       74
      ],
      "unresolved": [
       10
      ],
      "answered": [
       74
      ]
     },
     "rates": {
      "correct": [
       0.0
      ],
      "abstain": [
       0.3488372093023256
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.5736434108527132
      ],
      "unresolved": [
       0.07751937984496124
      ],
      "answered": [
       0.5736434108527132
      ]
     },
     "disp": {
      "correct": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "abstain": {
       "p0": "35",
       "p1": "34.9",
       "count": "45"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "57",
       "p1": "57.4",
       "count": "74"
      },
      "unresolved": {
       "p0": "8",
       "p1": "7.8",
       "count": "10"
      },
      "answered": {
       "p0": "57",
       "p1": "57.4",
       "count": "74"
      }
     }
    },
    "gemma3:12b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       0
      ],
      "abstain": [
       2
      ],
      "hedged": [
       0
      ],
      "other": [
       127
      ],
      "unresolved": [
       0
      ],
      "answered": [
       127
      ]
     },
     "rates": {
      "correct": [
       0.0
      ],
      "abstain": [
       0.015503875968992248
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9844961240310077
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.9844961240310077
      ]
     },
     "disp": {
      "correct": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "abstain": {
       "p0": "2",
       "p1": "1.6",
       "count": "2"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      }
     }
    },
    "gemma3:27b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       0
      ],
      "abstain": [
       2
      ],
      "hedged": [
       0
      ],
      "other": [
       127
      ],
      "unresolved": [
       0
      ],
      "answered": [
       127
      ]
     },
     "rates": {
      "correct": [
       0.0
      ],
      "abstain": [
       0.015503875968992248
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9844961240310077
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.9844961240310077
      ]
     },
     "disp": {
      "correct": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "abstain": {
       "p0": "2",
       "p1": "1.6",
       "count": "2"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      }
     }
    },
    "gemma4:12b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       1
      ],
      "abstain": [
       58
      ],
      "hedged": [
       0
      ],
      "other": [
       70
      ],
      "unresolved": [
       0
      ],
      "answered": [
       70
      ]
     },
     "rates": {
      "correct": [
       0.007751937984496124
      ],
      "abstain": [
       0.4496124031007752
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.5426356589147286
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.5426356589147286
      ]
     },
     "disp": {
      "correct": {
       "p0": "1",
       "p1": "0.8",
       "count": "1"
      },
      "abstain": {
       "p0": "45",
       "p1": "45.0",
       "count": "58"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "54",
       "p1": "54.3",
       "count": "70"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "54",
       "p1": "54.3",
       "count": "70"
      }
     }
    },
    "gemma4:26b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       1
      ],
      "abstain": [
       44
      ],
      "hedged": [
       1
      ],
      "other": [
       83
      ],
      "unresolved": [
       0
      ],
      "answered": [
       84
      ]
     },
     "rates": {
      "correct": [
       0.007751937984496124
      ],
      "abstain": [
       0.34108527131782945
      ],
      "hedged": [
       0.007751937984496124
      ],
      "other": [
       0.6434108527131783
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.6511627906976745
      ]
     },
     "disp": {
      "correct": {
       "p0": "1",
       "p1": "0.8",
       "count": "1"
      },
      "abstain": {
       "p0": "34",
       "p1": "34.1",
       "count": "44"
      },
      "hedged": {
       "p0": "1",
       "p1": "0.8",
       "count": "1"
      },
      "other": {
       "p0": "64",
       "p1": "64.3",
       "count": "83"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "65",
       "p1": "65.1",
       "count": "84"
      }
     }
    },
    "gpt-oss:120b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       0
      ],
      "abstain": [
       2
      ],
      "hedged": [
       0
      ],
      "other": [
       127
      ],
      "unresolved": [
       0
      ],
      "answered": [
       127
      ]
     },
     "rates": {
      "correct": [
       0.0
      ],
      "abstain": [
       0.015503875968992248
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9844961240310077
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.9844961240310077
      ]
     },
     "disp": {
      "correct": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "abstain": {
       "p0": "2",
       "p1": "1.6",
       "count": "2"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      }
     }
    },
    "gpt-oss:20b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       2
      ],
      "abstain": [
       0
      ],
      "hedged": [
       0
      ],
      "other": [
       127
      ],
      "unresolved": [
       0
      ],
      "answered": [
       127
      ]
     },
     "rates": {
      "correct": [
       0.015503875968992248
      ],
      "abstain": [
       0.0
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9844961240310077
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.9844961240310077
      ]
     },
     "disp": {
      "correct": {
       "p0": "2",
       "p1": "1.6",
       "count": "2"
      },
      "abstain": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      }
     }
    },
    "llama3.1:8b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       0
      ],
      "abstain": [
       2
      ],
      "hedged": [
       0
      ],
      "other": [
       127
      ],
      "unresolved": [
       0
      ],
      "answered": [
       127
      ]
     },
     "rates": {
      "correct": [
       0.0
      ],
      "abstain": [
       0.015503875968992248
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9844961240310077
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.9844961240310077
      ]
     },
     "disp": {
      "correct": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "abstain": {
       "p0": "2",
       "p1": "1.6",
       "count": "2"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      }
     }
    },
    "mistral-small3.2:24b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       2
      ],
      "abstain": [
       9
      ],
      "hedged": [
       0
      ],
      "other": [
       118
      ],
      "unresolved": [
       0
      ],
      "answered": [
       118
      ]
     },
     "rates": {
      "correct": [
       0.015503875968992248
      ],
      "abstain": [
       0.06976744186046512
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9147286821705426
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.9147286821705426
      ]
     },
     "disp": {
      "correct": {
       "p0": "2",
       "p1": "1.6",
       "count": "2"
      },
      "abstain": {
       "p0": "7",
       "p1": "7.0",
       "count": "9"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "91",
       "p1": "91.5",
       "count": "118"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "91",
       "p1": "91.5",
       "count": "118"
      }
     }
    },
    "phi4:14b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       0
      ],
      "abstain": [
       37
      ],
      "hedged": [
       1
      ],
      "other": [
       90
      ],
      "unresolved": [
       1
      ],
      "answered": [
       91
      ]
     },
     "rates": {
      "correct": [
       0.0
      ],
      "abstain": [
       0.2868217054263566
      ],
      "hedged": [
       0.007751937984496124
      ],
      "other": [
       0.6976744186046512
      ],
      "unresolved": [
       0.007751937984496124
      ],
      "answered": [
       0.7054263565891473
      ]
     },
     "disp": {
      "correct": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "abstain": {
       "p0": "29",
       "p1": "28.7",
       "count": "37"
      },
      "hedged": {
       "p0": "1",
       "p1": "0.8",
       "count": "1"
      },
      "other": {
       "p0": "70",
       "p1": "69.8",
       "count": "90"
      },
      "unresolved": {
       "p0": "1",
       "p1": "0.8",
       "count": "1"
      },
      "answered": {
       "p0": "71",
       "p1": "70.5",
       "count": "91"
      }
     }
    },
    "qwen3.5:27b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       0
      ],
      "abstain": [
       22
      ],
      "hedged": [
       0
      ],
      "other": [
       107
      ],
      "unresolved": [
       0
      ],
      "answered": [
       107
      ]
     },
     "rates": {
      "correct": [
       0.0
      ],
      "abstain": [
       0.17054263565891473
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.8294573643410853
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.8294573643410853
      ]
     },
     "disp": {
      "correct": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "abstain": {
       "p0": "17",
       "p1": "17.1",
       "count": "22"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "83",
       "p1": "82.9",
       "count": "107"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "83",
       "p1": "82.9",
       "count": "107"
      }
     }
    },
    "qwen3.5:9b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       0
      ],
      "abstain": [
       23
      ],
      "hedged": [
       0
      ],
      "other": [
       106
      ],
      "unresolved": [
       0
      ],
      "answered": [
       106
      ]
     },
     "rates": {
      "correct": [
       0.0
      ],
      "abstain": [
       0.17829457364341086
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.8217054263565892
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.8217054263565892
      ]
     },
     "disp": {
      "correct": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "abstain": {
       "p0": "18",
       "p1": "17.8",
       "count": "23"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "82",
       "p1": "82.2",
       "count": "106"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "82",
       "p1": "82.2",
       "count": "106"
      }
     }
    },
    "qwen3:14b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       0
      ],
      "abstain": [
       1
      ],
      "hedged": [
       0
      ],
      "other": [
       127
      ],
      "unresolved": [
       1
      ],
      "answered": [
       127
      ]
     },
     "rates": {
      "correct": [
       0.0
      ],
      "abstain": [
       0.007751937984496124
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9844961240310077
      ],
      "unresolved": [
       0.007751937984496124
      ],
      "answered": [
       0.9844961240310077
      ]
     },
     "disp": {
      "correct": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "abstain": {
       "p0": "1",
       "p1": "0.8",
       "count": "1"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      },
      "unresolved": {
       "p0": "1",
       "p1": "0.8",
       "count": "1"
      },
      "answered": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      }
     }
    },
    "qwen3:30b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       0
      ],
      "abstain": [
       8
      ],
      "hedged": [
       0
      ],
      "other": [
       121
      ],
      "unresolved": [
       0
      ],
      "answered": [
       121
      ]
     },
     "rates": {
      "correct": [
       0.0
      ],
      "abstain": [
       0.06201550387596899
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.937984496124031
      ],
      "unresolved": [
       0.0
      ],
      "answered": [
       0.937984496124031
      ]
     },
     "disp": {
      "correct": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "abstain": {
       "p0": "6",
       "p1": "6.2",
       "count": "8"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "94",
       "p1": "93.8",
       "count": "121"
      },
      "unresolved": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "answered": {
       "p0": "94",
       "p1": "93.8",
       "count": "121"
      }
     }
    },
    "qwen3:8b": {
     "runs": [
      1
     ],
     "n": [
      129
     ],
     "counts": {
      "correct": [
       0
      ],
      "abstain": [
       1
      ],
      "hedged": [
       0
      ],
      "other": [
       127
      ],
      "unresolved": [
       1
      ],
      "answered": [
       127
      ]
     },
     "rates": {
      "correct": [
       0.0
      ],
      "abstain": [
       0.007751937984496124
      ],
      "hedged": [
       0.0
      ],
      "other": [
       0.9844961240310077
      ],
      "unresolved": [
       0.007751937984496124
      ],
      "answered": [
       0.9844961240310077
      ]
     },
     "disp": {
      "correct": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "abstain": {
       "p0": "1",
       "p1": "0.8",
       "count": "1"
      },
      "hedged": {
       "p0": "0",
       "p1": "0.0",
       "count": "0"
      },
      "other": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      },
      "unresolved": {
       "p0": "1",
       "p1": "0.8",
       "count": "1"
      },
      "answered": {
       "p0": "98",
       "p1": "98.4",
       "count": "127"
      }
     }
    }
   },
   "ranges_models": {
    "plain|answerable|answered": {
     "lo": 0.0,
     "hi": 0.09302325581395349,
     "lo_model": "qwen3.5:27b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.08914728682170543,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.031007751937984496,
     "n_models": 16,
     "disp": {
      "p0": "0〜9",
      "p1": "0.0〜9.3"
     }
    },
    "plain|answerable|abstain": {
     "lo": 0.0,
     "hi": 0.015503875968992248,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3.5:9b",
     "mean_lo": 0.0,
     "mean_hi": 0.015503875968992248,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3.5:9b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜2",
      "p1": "0.0〜1.6"
     }
    },
    "plain|answerable|correct": {
     "lo": 0.8062015503875969,
     "hi": 1.0,
     "lo_model": "deepseek-r1:8b",
     "hi_model": "qwen3.5:27b",
     "mean_lo": 0.8217054263565892,
     "mean_hi": 1.0,
     "mean_lo_model": "deepseek-r1:8b",
     "mean_hi_model": "qwen3.5:27b",
     "median_of_means": 0.9670542635658915,
     "n_models": 16,
     "disp": {
      "p0": "81〜100",
      "p1": "80.6〜100.0"
     }
    },
    "plain|answerable|other": {
     "lo": 0.0,
     "hi": 0.09302325581395349,
     "lo_model": "qwen3.5:27b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.08914728682170543,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.031007751937984496,
     "n_models": 16,
     "disp": {
      "p0": "0〜9",
      "p1": "0.0〜9.3"
     }
    },
    "plain|answerable|hedged": {
     "lo": 0.0,
     "hi": 0.0,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.0,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0",
      "p1": "0.0"
     }
    },
    "plain|answerable|unresolved": {
     "lo": 0.0,
     "hi": 0.09302325581395349,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.07364341085271318,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜9",
      "p1": "0.0〜9.3"
     }
    },
    "plain|near|answered": {
     "lo": 0.17829457364341086,
     "hi": 0.8527131782945736,
     "lo_model": "qwen3.5:27b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.17829457364341086,
     "mean_hi": 0.8449612403100775,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.48255813953488375,
     "n_models": 16,
     "disp": {
      "p0": "18〜85",
      "p1": "17.8〜85.3"
     }
    },
    "plain|near|abstain": {
     "lo": 0.13953488372093023,
     "hi": 0.8217054263565892,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3.5:27b",
     "mean_lo": 0.1434108527131783,
     "mean_hi": 0.8217054263565892,
     "mean_lo_model": "qwen3:30b",
     "mean_hi_model": "qwen3.5:27b",
     "median_of_means": 0.4573643410852713,
     "n_models": 16,
     "disp": {
      "p0": "14〜82",
      "p1": "14.0〜82.2"
     }
    },
    "plain|near|correct": {
     "lo": 0.0,
     "hi": 0.015503875968992248,
     "lo_model": "qwen3:14b",
     "hi_model": "gemma3:27b",
     "mean_lo": 0.0,
     "mean_hi": 0.015503875968992248,
     "mean_lo_model": "qwen3:14b",
     "mean_hi_model": "gemma3:27b",
     "median_of_means": 0.003875968992248062,
     "n_models": 16,
     "disp": {
      "p0": "0〜2",
      "p1": "0.0〜1.6"
     }
    },
    "plain|near|other": {
     "lo": 0.17829457364341086,
     "hi": 0.8527131782945736,
     "lo_model": "qwen3.5:27b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.17829457364341086,
     "mean_hi": 0.8449612403100775,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.48255813953488375,
     "n_models": 16,
     "disp": {
      "p0": "18〜85",
      "p1": "17.8〜85.3"
     }
    },
    "plain|near|hedged": {
     "lo": 0.0,
     "hi": 0.007751937984496124,
     "lo_model": "qwen3:8b",
     "hi_model": "phi4:14b",
     "mean_lo": 0.0,
     "mean_hi": 0.007751937984496124,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "phi4:14b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜0.8"
     }
    },
    "plain|near|unresolved": {
     "lo": 0.0,
     "hi": 0.2713178294573643,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:30b",
     "mean_lo": 0.0,
     "mean_hi": 0.2441860465116279,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3:30b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜27",
      "p1": "0.0〜27.1"
     }
    },
    "plain|far|answered": {
     "lo": 0.007751937984496124,
     "hi": 0.8449612403100775,
     "lo_model": "qwen3.5:27b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.011627906976744186,
     "mean_hi": 0.8449612403100775,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.07945736434108527,
     "n_models": 16,
     "disp": {
      "p0": "1〜84",
      "p1": "0.8〜84.5"
     }
    },
    "plain|far|abstain": {
     "lo": 0.13178294573643412,
     "hi": 0.9922480620155039,
     "lo_model": "gpt-oss:20b",
     "hi_model": "qwen3.5:27b",
     "mean_lo": 0.13178294573643412,
     "mean_hi": 0.9883720930232558,
     "mean_lo_model": "gpt-oss:20b",
     "mean_hi_model": "qwen3.5:27b",
     "median_of_means": 0.9108527131782945,
     "n_models": 16,
     "disp": {
      "p0": "13〜99",
      "p1": "13.2〜99.2"
     }
    },
    "plain|far|correct": {
     "lo": 0.0,
     "hi": 0.023255813953488372,
     "lo_model": "qwen3:8b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.0,
     "mean_hi": 0.023255813953488372,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜2",
      "p1": "0.0〜2.3"
     }
    },
    "plain|far|other": {
     "lo": 0.007751937984496124,
     "hi": 0.8449612403100775,
     "lo_model": "qwen3.5:27b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.011627906976744186,
     "mean_hi": 0.8449612403100775,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.07945736434108527,
     "n_models": 16,
     "disp": {
      "p0": "1〜84",
      "p1": "0.8〜84.5"
     }
    },
    "plain|far|hedged": {
     "lo": 0.0,
     "hi": 0.0,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.0,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0",
      "p1": "0.0"
     }
    },
    "plain|far|unresolved": {
     "lo": 0.0,
     "hi": 0.10852713178294573,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.08914728682170543,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜11",
      "p1": "0.0〜10.9"
     }
    },
    "abstain|answerable|answered": {
     "lo": 0.0,
     "hi": 0.10077519379844961,
     "lo_model": "qwen3.5:9b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.09689922480620156,
     "mean_lo_model": "qwen3.5:9b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.02131782945736434,
     "n_models": 16,
     "disp": {
      "p0": "0〜10",
      "p1": "0.0〜10.1"
     }
    },
    "abstain|answerable|abstain": {
     "lo": 0.0,
     "hi": 0.13178294573643412,
     "lo_model": "gpt-oss:20b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.003875968992248062,
     "mean_hi": 0.10852713178294573,
     "mean_lo_model": "gpt-oss:20b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.025193798449612403,
     "n_models": 16,
     "disp": {
      "p0": "0〜13",
      "p1": "0.0〜13.2"
     }
    },
    "abstain|answerable|correct": {
     "lo": 0.7674418604651163,
     "hi": 0.9767441860465116,
     "lo_model": "deepseek-r1:8b",
     "hi_model": "qwen3.5:27b",
     "mean_lo": 0.7906976744186046,
     "mean_hi": 0.9767441860465116,
     "mean_lo_model": "deepseek-r1:8b",
     "mean_hi_model": "qwen3.5:27b",
     "median_of_means": 0.9476744186046512,
     "n_models": 16,
     "disp": {
      "p0": "77〜98",
      "p1": "76.7〜97.7"
     }
    },
    "abstain|answerable|other": {
     "lo": 0.0,
     "hi": 0.10077519379844961,
     "lo_model": "qwen3.5:9b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.09689922480620156,
     "mean_lo_model": "qwen3.5:9b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.01937984496124031,
     "n_models": 16,
     "disp": {
      "p0": "0〜10",
      "p1": "0.0〜10.1"
     }
    },
    "abstain|answerable|hedged": {
     "lo": 0.0,
     "hi": 0.007751937984496124,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.007751937984496124,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "phi4:14b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜0.8"
     }
    },
    "abstain|answerable|unresolved": {
     "lo": 0.0,
     "hi": 0.05426356589147287,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.04263565891472868,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜5",
      "p1": "0.0〜5.4"
     }
    },
    "abstain|near|answered": {
     "lo": 0.007751937984496124,
     "hi": 0.23255813953488372,
     "lo_model": "qwen3.5:27b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.007751937984496124,
     "mean_hi": 0.22868217054263565,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.11046511627906977,
     "n_models": 16,
     "disp": {
      "p0": "1〜23",
      "p1": "0.8〜23.3"
     }
    },
    "abstain|near|abstain": {
     "lo": 0.6976744186046512,
     "hi": 0.9922480620155039,
     "lo_model": "llama3.1:8b",
     "hi_model": "qwen3.5:27b",
     "mean_lo": 0.7015503875968992,
     "mean_hi": 0.9922480620155039,
     "mean_lo_model": "llama3.1:8b",
     "mean_hi_model": "qwen3.5:27b",
     "median_of_means": 0.877906976744186,
     "n_models": 16,
     "disp": {
      "p0": "70〜99",
      "p1": "69.8〜99.2"
     }
    },
    "abstain|near|correct": {
     "lo": 0.0,
     "hi": 0.007751937984496124,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:30b",
     "mean_lo": 0.0,
     "mean_hi": 0.007751937984496124,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3:30b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜0.8"
     }
    },
    "abstain|near|other": {
     "lo": 0.007751937984496124,
     "hi": 0.23255813953488372,
     "lo_model": "qwen3.5:27b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.007751937984496124,
     "mean_hi": 0.22868217054263565,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.11046511627906977,
     "n_models": 16,
     "disp": {
      "p0": "1〜23",
      "p1": "0.8〜23.3"
     }
    },
    "abstain|near|hedged": {
     "lo": 0.0,
     "hi": 0.007751937984496124,
     "lo_model": "qwen3:14b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.007751937984496124,
     "mean_lo_model": "qwen3:14b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜0.8"
     }
    },
    "abstain|near|unresolved": {
     "lo": 0.0,
     "hi": 0.15503875968992248,
     "lo_model": "qwen3:8b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.1511627906976744,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜16",
      "p1": "0.0〜15.5"
     }
    },
    "abstain|far|answered": {
     "lo": 0.0,
     "hi": 0.031007751937984496,
     "lo_model": "qwen3:8b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.0,
     "mean_hi": 0.027131782945736434,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜3",
      "p1": "0.0〜3.1"
     }
    },
    "abstain|far|abstain": {
     "lo": 0.9689922480620154,
     "hi": 1.0,
     "lo_model": "gpt-oss:20b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.9728682170542635,
     "mean_hi": 1.0,
     "mean_lo_model": "gpt-oss:20b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 1.0,
     "n_models": 16,
     "disp": {
      "p0": "97〜100",
      "p1": "96.9〜100.0"
     }
    },
    "abstain|far|correct": {
     "lo": 0.0,
     "hi": 0.0,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.0,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0",
      "p1": "0.0"
     }
    },
    "abstain|far|other": {
     "lo": 0.0,
     "hi": 0.031007751937984496,
     "lo_model": "qwen3:8b",
     "hi_model": "gpt-oss:20b",
     "mean_lo": 0.0,
     "mean_hi": 0.027131782945736434,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "gpt-oss:20b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜3",
      "p1": "0.0〜3.1"
     }
    },
    "abstain|far|hedged": {
     "lo": 0.0,
     "hi": 0.0,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.0,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0",
      "p1": "0.0"
     }
    },
    "abstain|far|unresolved": {
     "lo": 0.0,
     "hi": 0.023255813953488372,
     "lo_model": "qwen3:8b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.01937984496124031,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜2",
      "p1": "0.0〜2.3"
     }
    },
    "quote|answerable|answered": {
     "lo": 0.0,
     "hi": 0.10852713178294573,
     "lo_model": "qwen3.5:27b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.10465116279069768,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.01937984496124031,
     "n_models": 16,
     "disp": {
      "p0": "0〜11",
      "p1": "0.0〜10.9"
     }
    },
    "quote|answerable|abstain": {
     "lo": 0.0,
     "hi": 0.35658914728682173,
     "lo_model": "qwen3.5:27b",
     "hi_model": "qwen3.5:9b",
     "mean_lo": 0.0,
     "mean_hi": 0.35658914728682173,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "qwen3.5:9b",
     "median_of_means": 0.015503875968992248,
     "n_models": 16,
     "disp": {
      "p0": "0〜36",
      "p1": "0.0〜35.7"
     }
    },
    "quote|answerable|correct": {
     "lo": 0.627906976744186,
     "hi": 1.0,
     "lo_model": "qwen3.5:9b",
     "hi_model": "qwen3.5:27b",
     "mean_lo": 0.627906976744186,
     "mean_hi": 1.0,
     "mean_lo_model": "qwen3.5:9b",
     "mean_hi_model": "qwen3.5:27b",
     "median_of_means": 0.9631782945736435,
     "n_models": 16,
     "disp": {
      "p0": "63〜100",
      "p1": "62.8〜100.0"
     }
    },
    "quote|answerable|other": {
     "lo": 0.0,
     "hi": 0.10852713178294573,
     "lo_model": "qwen3.5:27b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.10465116279069768,
     "mean_lo_model": "qwen3.5:27b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.01937984496124031,
     "n_models": 16,
     "disp": {
      "p0": "0〜11",
      "p1": "0.0〜10.9"
     }
    },
    "quote|answerable|hedged": {
     "lo": 0.0,
     "hi": 0.007751937984496124,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:14b",
     "mean_lo": 0.0,
     "mean_hi": 0.003875968992248062,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "deepseek-r1:14b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜0.8"
     }
    },
    "quote|answerable|unresolved": {
     "lo": 0.0,
     "hi": 0.05426356589147287,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.046511627906976744,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜5",
      "p1": "0.0〜5.4"
     }
    },
    "quote|near|answered": {
     "lo": 0.03875968992248062,
     "hi": 0.6434108527131783,
     "lo_model": "qwen3.5:9b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.03875968992248062,
     "mean_hi": 0.624031007751938,
     "mean_lo_model": "qwen3.5:9b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.1182170542635659,
     "n_models": 16,
     "disp": {
      "p0": "4〜64",
      "p1": "3.9〜64.3"
     }
    },
    "quote|near|abstain": {
     "lo": 0.3333333333333333,
     "hi": 0.9612403100775194,
     "lo_model": "llama3.1:8b",
     "hi_model": "qwen3.5:9b",
     "mean_lo": 0.34108527131782945,
     "mean_hi": 0.9612403100775194,
     "mean_lo_model": "llama3.1:8b",
     "mean_hi_model": "qwen3.5:9b",
     "median_of_means": 0.8662790697674418,
     "n_models": 16,
     "disp": {
      "p0": "33〜96",
      "p1": "33.3〜96.1"
     }
    },
    "quote|near|correct": {
     "lo": 0.0,
     "hi": 0.007751937984496124,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:30b",
     "mean_lo": 0.0,
     "mean_hi": 0.007751937984496124,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "gemma3:27b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜0.8"
     }
    },
    "quote|near|other": {
     "lo": 0.03875968992248062,
     "hi": 0.6434108527131783,
     "lo_model": "qwen3.5:9b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.03875968992248062,
     "mean_hi": 0.624031007751938,
     "mean_lo_model": "qwen3.5:9b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.11627906976744186,
     "n_models": 16,
     "disp": {
      "p0": "4〜64",
      "p1": "3.9〜64.3"
     }
    },
    "quote|near|hedged": {
     "lo": 0.0,
     "hi": 0.007751937984496124,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.003875968992248062,
     "mean_lo_model": "qwen3:14b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜1",
      "p1": "0.0〜0.8"
     }
    },
    "quote|near|unresolved": {
     "lo": 0.0,
     "hi": 0.12403100775193798,
     "lo_model": "qwen3:14b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.11627906976744186,
     "mean_lo_model": "qwen3:14b",
     "mean_hi_model": "deepseek-r1:8b",
     "median_of_means": 0.001937984496124031,
     "n_models": 16,
     "disp": {
      "p0": "0〜12",
      "p1": "0.0〜12.4"
     }
    },
    "quote|far|answered": {
     "lo": 0.0,
     "hi": 0.2713178294573643,
     "lo_model": "qwen3:8b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.26356589147286824,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜27",
      "p1": "0.0〜27.1"
     }
    },
    "quote|far|abstain": {
     "lo": 0.7054263565891473,
     "hi": 1.0,
     "lo_model": "llama3.1:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.7131782945736435,
     "mean_hi": 1.0,
     "mean_lo_model": "llama3.1:8b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.998062015503876,
     "n_models": 16,
     "disp": {
      "p0": "71〜100",
      "p1": "70.5〜100.0"
     }
    },
    "quote|far|correct": {
     "lo": 0.0,
     "hi": 0.0,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.0,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0",
      "p1": "0.0"
     }
    },
    "quote|far|other": {
     "lo": 0.0,
     "hi": 0.2713178294573643,
     "lo_model": "qwen3:8b",
     "hi_model": "llama3.1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.26356589147286824,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜27",
      "p1": "0.0〜27.1"
     }
    },
    "quote|far|hedged": {
     "lo": 0.0,
     "hi": 0.0,
     "lo_model": "qwen3:8b",
     "hi_model": "qwen3:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.0,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "qwen3:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0",
      "p1": "0.0"
     }
    },
    "quote|far|unresolved": {
     "lo": 0.0,
     "hi": 0.023255813953488372,
     "lo_model": "qwen3:8b",
     "hi_model": "deepseek-r1:8b",
     "mean_lo": 0.0,
     "mean_hi": 0.023255813953488372,
     "mean_lo_model": "qwen3:8b",
     "mean_hi_model": "llama3.1:8b",
     "median_of_means": 0.0,
     "n_models": 16,
     "disp": {
      "p0": "0〜2",
      "p1": "0.0〜2.3"
     }
    }
   },
   "tests": {
    "near_answered": {
     "title": "近い話題で答えを出した（答えを出した＋断りながら答えた）",
     "condition": "near",
     "finals": [
      "other",
      "hedged"
     ],
     "models": {
      "qwen3:8b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 38,
         "plain_only": 91,
         "abstain_only": 0,
         "p": 8.077935669463161e-28,
         "p_holm": 1.2924697071141057e-26,
         "plain_rate": 0.8527131782945736,
         "abstain_rate": 0.14728682170542637
        },
        {
         "n_pairs": 129,
         "n_ties": 40,
         "plain_only": 89,
         "abstain_only": 0,
         "p": 3.2311742677852644e-27,
         "p_holm": 5.169878828456423e-26,
         "plain_rate": 0.8372093023255814,
         "abstain_rate": 0.14728682170542637
        }
       ],
       "p_holm_max": 5.169878828456423e-26,
       "significant_both": true,
       "plain_greater_both": true
      },
      "qwen3:14b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 55,
         "plain_only": 74,
         "abstain_only": 0,
         "p": 1.0587911840678754e-22,
         "p_holm": 1.376428539288238e-21,
         "plain_rate": 0.7131782945736435,
         "abstain_rate": 0.13953488372093023
        },
        {
         "n_pairs": 129,
         "n_ties": 51,
         "plain_only": 78,
         "abstain_only": 0,
         "p": 6.617444900424222e-24,
         "p_holm": 8.602678370551488e-23,
         "plain_rate": 0.7441860465116279,
         "abstain_rate": 0.13953488372093023
        }
       ],
       "p_holm_max": 1.376428539288238e-21,
       "significant_both": true,
       "plain_greater_both": true
      },
      "qwen3:30b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 68,
         "plain_only": 60,
         "abstain_only": 1,
         "p": 5.377642775528102e-17,
         "p_holm": 5.377642775528102e-16,
         "plain_rate": 0.627906976744186,
         "abstain_rate": 0.17054263565891473
        },
        {
         "n_pairs": 129,
         "n_ties": 71,
         "plain_only": 55,
         "abstain_only": 3,
         "p": 2.2598589666245061e-13,
         "p_holm": 2.0338730699620555e-12,
         "plain_rate": 0.5813953488372093,
         "abstain_rate": 0.17829457364341086
        }
       ],
       "p_holm_max": 2.0338730699620555e-12,
       "significant_both": true,
       "plain_greater_both": true
      },
      "qwen3.5:9b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 92,
         "plain_only": 37,
         "abstain_only": 0,
         "p": 1.4551915228366852e-11,
         "p_holm": 1.0186340659856796e-10,
         "plain_rate": 0.37209302325581395,
         "abstain_rate": 0.08527131782945736
        },
        {
         "n_pairs": 129,
         "n_ties": 91,
         "plain_only": 38,
         "abstain_only": 0,
         "p": 7.275957614183426e-12,
         "p_holm": 5.820766091346741e-11,
         "plain_rate": 0.3798449612403101,
         "abstain_rate": 0.08527131782945736
        }
       ],
       "p_holm_max": 1.0186340659856796e-10,
       "significant_both": true,
       "plain_greater_both": true
      },
      "qwen3.5:27b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 107,
         "plain_only": 22,
         "abstain_only": 0,
         "p": 4.76837158203125e-07,
         "p_holm": 1.430511474609375e-06,
         "plain_rate": 0.17829457364341086,
         "abstain_rate": 0.007751937984496124
        },
        {
         "n_pairs": 129,
         "n_ties": 107,
         "plain_only": 22,
         "abstain_only": 0,
         "p": 4.76837158203125e-07,
         "p_holm": 1.3886019587516785e-06,
         "plain_rate": 0.17829457364341086,
         "abstain_rate": 0.007751937984496124
        }
       ],
       "p_holm_max": 1.430511474609375e-06,
       "significant_both": true,
       "plain_greater_both": true
      },
      "gemma3:12b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 97,
         "plain_only": 31,
         "abstain_only": 1,
         "p": 1.5366822481155396e-08,
         "p_holm": 7.450580596923828e-08,
         "plain_rate": 0.3643410852713178,
         "abstain_rate": 0.13178294573643412
        },
        {
         "n_pairs": 129,
         "n_ties": 98,
         "plain_only": 29,
         "abstain_only": 2,
         "p": 4.628673195838928e-07,
         "p_holm": 1.3886019587516785e-06,
         "plain_rate": 0.3488372093023256,
         "abstain_rate": 0.13953488372093023
        }
       ],
       "p_holm_max": 1.3886019587516785e-06,
       "significant_both": true,
       "plain_greater_both": true
      },
      "gemma3:27b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 92,
         "plain_only": 37,
         "abstain_only": 0,
         "p": 1.4551915228366852e-11,
         "p_holm": 1.0186340659856796e-10,
         "plain_rate": 0.4728682170542636,
         "abstain_rate": 0.18604651162790697
        },
        {
         "n_pairs": 129,
         "n_ties": 93,
         "plain_only": 36,
         "abstain_only": 0,
         "p": 2.9103830456733704e-11,
         "p_holm": 1.7462298274040222e-10,
         "plain_rate": 0.4573643410852713,
         "abstain_rate": 0.17829457364341086
        }
       ],
       "p_holm_max": 1.7462298274040222e-10,
       "significant_both": true,
       "plain_greater_both": true
      },
      "gemma4:12b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 102,
         "plain_only": 27,
         "abstain_only": 0,
         "p": 1.4901161193847656e-08,
         "p_holm": 7.450580596923828e-08,
         "plain_rate": 0.2868217054263566,
         "abstain_rate": 0.07751937984496124
        },
        {
         "n_pairs": 129,
         "n_ties": 103,
         "plain_only": 26,
         "abstain_only": 0,
         "p": 2.9802322387695312e-08,
         "p_holm": 1.4901161193847656e-07,
         "plain_rate": 0.2868217054263566,
         "abstain_rate": 0.08527131782945736
        }
       ],
       "p_holm_max": 1.4901161193847656e-07,
       "significant_both": true,
       "plain_greater_both": true
      },
      "gemma4:26b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 111,
         "plain_only": 18,
         "abstain_only": 0,
         "p": 7.62939453125e-06,
         "p_holm": 7.62939453125e-06,
         "plain_rate": 0.21705426356589147,
         "abstain_rate": 0.07751937984496124
        },
        {
         "n_pairs": 129,
         "n_ties": 115,
         "plain_only": 14,
         "abstain_only": 0,
         "p": 0.0001220703125,
         "p_holm": 0.0001220703125,
         "plain_rate": 0.1937984496124031,
         "abstain_rate": 0.08527131782945736
        }
       ],
       "p_holm_max": 0.0001220703125,
       "significant_both": true,
       "plain_greater_both": true
      },
      "gpt-oss:20b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 57,
         "plain_only": 72,
         "abstain_only": 0,
         "p": 4.235164736271502e-22,
         "p_holm": 5.082197683525802e-21,
         "plain_rate": 0.7906976744186046,
         "abstain_rate": 0.23255813953488372
        },
        {
         "n_pairs": 129,
         "n_ties": 51,
         "plain_only": 77,
         "abstain_only": 1,
         "p": 5.227781471335135e-22,
         "p_holm": 6.273337765602162e-21,
         "plain_rate": 0.813953488372093,
         "abstain_rate": 0.2248062015503876
        }
       ],
       "p_holm_max": 6.273337765602162e-21,
       "significant_both": true,
       "plain_greater_both": true
      },
      "gpt-oss:120b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 43,
         "plain_only": 86,
         "abstain_only": 0,
         "p": 2.5849394142282115e-26,
         "p_holm": 3.877409121342317e-25,
         "plain_rate": 0.7364341085271318,
         "abstain_rate": 0.06976744186046512
        },
        {
         "n_pairs": 129,
         "n_ties": 44,
         "plain_only": 85,
         "abstain_only": 0,
         "p": 5.169878828456423e-26,
         "p_holm": 7.754818242684634e-25,
         "plain_rate": 0.7286821705426356,
         "abstain_rate": 0.06976744186046512
        }
       ],
       "p_holm_max": 7.754818242684634e-25,
       "significant_both": true,
       "plain_greater_both": true
      },
      "deepseek-r1:8b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 84,
         "plain_only": 39,
         "abstain_only": 6,
         "p": 5.417768988991156e-07,
         "p_holm": 1.430511474609375e-06,
         "plain_rate": 0.3798449612403101,
         "abstain_rate": 0.12403100775193798
        },
        {
         "n_pairs": 129,
         "n_ties": 84,
         "plain_only": 40,
         "abstain_only": 5,
         "p": 7.878384167270269e-08,
         "p_holm": 3.1513536669081077e-07,
         "plain_rate": 0.37209302325581395,
         "abstain_rate": 0.10077519379844961
        }
       ],
       "p_holm_max": 1.430511474609375e-06,
       "significant_both": true,
       "plain_greater_both": true
      },
      "deepseek-r1:14b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 73,
         "plain_only": 54,
         "abstain_only": 2,
         "p": 4.4325654258159375e-14,
         "p_holm": 3.9893088832343437e-13,
         "plain_rate": 0.5038759689922481,
         "abstain_rate": 0.10077519379844961
        },
        {
         "n_pairs": 129,
         "n_ties": 75,
         "plain_only": 53,
         "abstain_only": 1,
         "p": 6.106226635438361e-15,
         "p_holm": 6.106226635438361e-14,
         "plain_rate": 0.49612403100775193,
         "abstain_rate": 0.09302325581395349
        }
       ],
       "p_holm_max": 3.9893088832343437e-13,
       "significant_both": true,
       "plain_greater_both": true
      },
      "llama3.1:8b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 46,
         "plain_only": 83,
         "abstain_only": 0,
         "p": 2.0679515313825692e-25,
         "p_holm": 2.895132143935597e-24,
         "plain_rate": 0.7906976744186046,
         "abstain_rate": 0.14728682170542637
        },
        {
         "n_pairs": 129,
         "n_ties": 45,
         "plain_only": 84,
         "abstain_only": 0,
         "p": 1.0339757656912846e-25,
         "p_holm": 1.4475660719677984e-24,
         "plain_rate": 0.7984496124031008,
         "abstain_rate": 0.14728682170542637
        }
       ],
       "p_holm_max": 2.895132143935597e-24,
       "significant_both": true,
       "plain_greater_both": true
      },
      "mistral-small3.2:24b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 73,
         "plain_only": 56,
         "abstain_only": 0,
         "p": 2.7755575615628914e-17,
         "p_holm": 3.0531133177191805e-16,
         "plain_rate": 0.5426356589147286,
         "abstain_rate": 0.10852713178294573
        },
        {
         "n_pairs": 129,
         "n_ties": 71,
         "plain_only": 58,
         "abstain_only": 0,
         "p": 6.938893903907228e-18,
         "p_holm": 7.632783294297951e-17,
         "plain_rate": 0.5581395348837209,
         "abstain_rate": 0.10852713178294573
        }
       ],
       "p_holm_max": 3.0531133177191805e-16,
       "significant_both": true,
       "plain_greater_both": true
      },
      "phi4:14b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 89,
         "plain_only": 40,
         "abstain_only": 0,
         "p": 1.8189894035458565e-12,
         "p_holm": 1.4551915228366852e-11,
         "plain_rate": 0.3643410852713178,
         "abstain_rate": 0.05426356589147287
        },
        {
         "n_pairs": 129,
         "n_ties": 91,
         "plain_only": 38,
         "abstain_only": 0,
         "p": 7.275957614183426e-12,
         "p_holm": 5.820766091346741e-11,
         "plain_rate": 0.3488372093023256,
         "abstain_rate": 0.05426356589147287
        }
       ],
       "p_holm_max": 5.820766091346741e-11,
       "significant_both": true,
       "plain_greater_both": true
      }
     },
     "n_significant_both": 16
    },
    "answerable_correct": {
     "title": "答えありで正答",
     "condition": "answerable",
     "finals": [
      "correct"
     ],
     "models": {
      "qwen3:8b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 125,
         "plain_only": 4,
         "abstain_only": 0,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.937984496124031,
         "abstain_rate": 0.9069767441860465
        },
        {
         "n_pairs": 129,
         "n_ties": 124,
         "plain_only": 4,
         "abstain_only": 1,
         "p": 0.375,
         "p_holm": 1.0,
         "plain_rate": 0.9302325581395349,
         "abstain_rate": 0.9069767441860465
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "qwen3:14b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 126,
         "plain_only": 2,
         "abstain_only": 1,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9767441860465116,
         "abstain_rate": 0.9689922480620154
        },
        {
         "n_pairs": 129,
         "n_ties": 126,
         "plain_only": 2,
         "abstain_only": 1,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9689922480620154,
         "abstain_rate": 0.9612403100775194
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "qwen3:30b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 125,
         "plain_only": 1,
         "abstain_only": 3,
         "p": 0.625,
         "p_holm": 1.0,
         "plain_rate": 0.937984496124031,
         "abstain_rate": 0.9534883720930233
        },
        {
         "n_pairs": 129,
         "n_ties": 123,
         "plain_only": 3,
         "abstain_only": 3,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.937984496124031,
         "abstain_rate": 0.937984496124031
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "qwen3.5:9b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 121,
         "plain_only": 5,
         "abstain_only": 3,
         "p": 0.7265625,
         "p_holm": 1.0,
         "plain_rate": 0.9612403100775194,
         "abstain_rate": 0.9457364341085271
        },
        {
         "n_pairs": 129,
         "n_ties": 122,
         "plain_only": 5,
         "abstain_only": 2,
         "p": 0.453125,
         "p_holm": 1.0,
         "plain_rate": 0.9689922480620154,
         "abstain_rate": 0.9457364341085271
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "qwen3.5:27b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 126,
         "plain_only": 3,
         "abstain_only": 0,
         "p": 0.25,
         "p_holm": 1.0,
         "plain_rate": 1.0,
         "abstain_rate": 0.9767441860465116
        },
        {
         "n_pairs": 129,
         "n_ties": 126,
         "plain_only": 3,
         "abstain_only": 0,
         "p": 0.25,
         "p_holm": 1.0,
         "plain_rate": 1.0,
         "abstain_rate": 0.9767441860465116
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "gemma3:12b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 126,
         "plain_only": 3,
         "abstain_only": 0,
         "p": 0.25,
         "p_holm": 1.0,
         "plain_rate": 0.9689922480620154,
         "abstain_rate": 0.9457364341085271
        },
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 2,
         "abstain_only": 0,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.9689922480620154,
         "abstain_rate": 0.9534883720930233
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "gemma3:27b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 125,
         "plain_only": 2,
         "abstain_only": 2,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9689922480620154,
         "abstain_rate": 0.9689922480620154
        },
        {
         "n_pairs": 129,
         "n_ties": 125,
         "plain_only": 2,
         "abstain_only": 2,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9689922480620154,
         "abstain_rate": 0.9689922480620154
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gemma4:12b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 123,
         "plain_only": 5,
         "abstain_only": 1,
         "p": 0.21875,
         "p_holm": 1.0,
         "plain_rate": 0.9844961240310077,
         "abstain_rate": 0.9534883720930233
        },
        {
         "n_pairs": 129,
         "n_ties": 124,
         "plain_only": 4,
         "abstain_only": 1,
         "p": 0.375,
         "p_holm": 1.0,
         "plain_rate": 0.9844961240310077,
         "abstain_rate": 0.9612403100775194
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "gemma4:26b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 128,
         "plain_only": 1,
         "abstain_only": 0,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9844961240310077,
         "abstain_rate": 0.9767441860465116
        },
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 2,
         "abstain_only": 0,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.9844961240310077,
         "abstain_rate": 0.9689922480620154
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "gpt-oss:20b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 2,
         "abstain_only": 0,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.9844961240310077,
         "abstain_rate": 0.9689922480620154
        },
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 2,
         "abstain_only": 0,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.9844961240310077,
         "abstain_rate": 0.9689922480620154
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "gpt-oss:120b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 122,
         "plain_only": 4,
         "abstain_only": 3,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9767441860465116,
         "abstain_rate": 0.9689922480620154
        },
        {
         "n_pairs": 129,
         "n_ties": 121,
         "plain_only": 4,
         "abstain_only": 4,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.9612403100775194,
         "abstain_rate": 0.9612403100775194
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "deepseek-r1:8b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 104,
         "plain_only": 12,
         "abstain_only": 13,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.8062015503875969,
         "abstain_rate": 0.813953488372093
        },
        {
         "n_pairs": 129,
         "n_ties": 98,
         "plain_only": 20,
         "abstain_only": 11,
         "p": 0.14961278438568115,
         "p_holm": 1.0,
         "plain_rate": 0.8372093023255814,
         "abstain_rate": 0.7674418604651163
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "deepseek-r1:14b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 123,
         "plain_only": 4,
         "abstain_only": 2,
         "p": 0.6875,
         "p_holm": 1.0,
         "plain_rate": 0.9534883720930233,
         "abstain_rate": 0.937984496124031
        },
        {
         "n_pairs": 129,
         "n_ties": 120,
         "plain_only": 4,
         "abstain_only": 5,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.937984496124031,
         "abstain_rate": 0.9457364341085271
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "llama3.1:8b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 115,
         "plain_only": 14,
         "abstain_only": 0,
         "p": 0.0001220703125,
         "p_holm": 0.001953125,
         "plain_rate": 0.937984496124031,
         "abstain_rate": 0.8294573643410853
        },
        {
         "n_pairs": 129,
         "n_ties": 113,
         "plain_only": 16,
         "abstain_only": 0,
         "p": 3.0517578125e-05,
         "p_holm": 0.00048828125,
         "plain_rate": 0.9457364341085271,
         "abstain_rate": 0.8217054263565892
        }
       ],
       "p_holm_max": 0.001953125,
       "significant_both": true,
       "plain_greater_both": true
      },
      "mistral-small3.2:24b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 123,
         "plain_only": 4,
         "abstain_only": 2,
         "p": 0.6875,
         "p_holm": 1.0,
         "plain_rate": 0.9612403100775194,
         "abstain_rate": 0.9457364341085271
        },
        {
         "n_pairs": 129,
         "n_ties": 123,
         "plain_only": 4,
         "abstain_only": 2,
         "p": 0.6875,
         "p_holm": 1.0,
         "plain_rate": 0.9612403100775194,
         "abstain_rate": 0.9457364341085271
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": true
      },
      "phi4:14b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 118,
         "plain_only": 11,
         "abstain_only": 0,
         "p": 0.0009765625,
         "p_holm": 0.0146484375,
         "plain_rate": 0.9612403100775194,
         "abstain_rate": 0.875968992248062
        },
        {
         "n_pairs": 129,
         "n_ties": 117,
         "plain_only": 12,
         "abstain_only": 0,
         "p": 0.00048828125,
         "p_holm": 0.00732421875,
         "plain_rate": 0.9612403100775194,
         "abstain_rate": 0.8682170542635659
        }
       ],
       "p_holm_max": 0.0146484375,
       "significant_both": true,
       "plain_greater_both": true
      }
     },
     "n_significant_both": 2
    },
    "answerable_abstain": {
     "title": "答えありで不要な辞退",
     "condition": "answerable",
     "finals": [
      "abstain"
     ],
     "models": {
      "qwen3:8b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 126,
         "plain_only": 0,
         "abstain_only": 3,
         "p": 0.25,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.023255813953488372
        },
        {
         "n_pairs": 129,
         "n_ties": 126,
         "plain_only": 0,
         "abstain_only": 3,
         "p": 0.25,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.023255813953488372
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "qwen3:14b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.015503875968992248
        },
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.015503875968992248
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "qwen3:30b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.015503875968992248
        },
        {
         "n_pairs": 129,
         "n_ties": 128,
         "plain_only": 0,
         "abstain_only": 1,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.007751937984496124
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "qwen3.5:9b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 124,
         "plain_only": 0,
         "abstain_only": 5,
         "p": 0.0625,
         "p_holm": 0.875,
         "plain_rate": 0.015503875968992248,
         "abstain_rate": 0.05426356589147287
        },
        {
         "n_pairs": 129,
         "n_ties": 124,
         "plain_only": 0,
         "abstain_only": 5,
         "p": 0.0625,
         "p_holm": 0.875,
         "plain_rate": 0.015503875968992248,
         "abstain_rate": 0.05426356589147287
        }
       ],
       "p_holm_max": 0.875,
       "significant_both": false,
       "plain_greater_both": false
      },
      "qwen3.5:27b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 126,
         "plain_only": 0,
         "abstain_only": 3,
         "p": 0.25,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.023255813953488372
        },
        {
         "n_pairs": 129,
         "n_ties": 126,
         "plain_only": 0,
         "abstain_only": 3,
         "p": 0.25,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.023255813953488372
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gemma3:12b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.015503875968992248
        },
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.015503875968992248
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gemma3:27b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.015503875968992248
        },
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.015503875968992248
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gemma4:12b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 124,
         "plain_only": 0,
         "abstain_only": 5,
         "p": 0.0625,
         "p_holm": 0.875,
         "plain_rate": 0.0,
         "abstain_rate": 0.03875968992248062
        },
        {
         "n_pairs": 129,
         "n_ties": 125,
         "plain_only": 0,
         "abstain_only": 4,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.031007751937984496
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gemma4:26b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 128,
         "plain_only": 0,
         "abstain_only": 1,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.015503875968992248,
         "abstain_rate": 0.023255813953488372
        },
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.015503875968992248,
         "abstain_rate": 0.031007751937984496
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gpt-oss:20b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 128,
         "plain_only": 0,
         "abstain_only": 1,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.007751937984496124
        },
        {
         "n_pairs": 129,
         "n_ties": 129,
         "plain_only": 0,
         "abstain_only": 0,
         "p": 1.0,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.0
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "gpt-oss:120b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.015503875968992248
        },
        {
         "n_pairs": 129,
         "n_ties": 127,
         "plain_only": 0,
         "abstain_only": 2,
         "p": 0.5,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.015503875968992248
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "deepseek-r1:8b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 116,
         "plain_only": 2,
         "abstain_only": 11,
         "p": 0.0224609375,
         "p_holm": 0.3369140625,
         "plain_rate": 0.015503875968992248,
         "abstain_rate": 0.08527131782945736
        },
        {
         "n_pairs": 129,
         "n_ties": 114,
         "plain_only": 0,
         "abstain_only": 15,
         "p": 6.103515625e-05,
         "p_holm": 0.0009765625,
         "plain_rate": 0.015503875968992248,
         "abstain_rate": 0.13178294573643412
        }
       ],
       "p_holm_max": 0.3369140625,
       "significant_both": false,
       "plain_greater_both": false
      },
      "deepseek-r1:14b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 124,
         "plain_only": 0,
         "abstain_only": 5,
         "p": 0.0625,
         "p_holm": 0.875,
         "plain_rate": 0.0,
         "abstain_rate": 0.03875968992248062
        },
        {
         "n_pairs": 129,
         "n_ties": 125,
         "plain_only": 0,
         "abstain_only": 4,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.007751937984496124,
         "abstain_rate": 0.03875968992248062
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "llama3.1:8b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 124,
         "plain_only": 0,
         "abstain_only": 5,
         "p": 0.0625,
         "p_holm": 0.875,
         "plain_rate": 0.0,
         "abstain_rate": 0.03875968992248062
        },
        {
         "n_pairs": 129,
         "n_ties": 124,
         "plain_only": 0,
         "abstain_only": 5,
         "p": 0.0625,
         "p_holm": 0.875,
         "plain_rate": 0.0,
         "abstain_rate": 0.03875968992248062
        }
       ],
       "p_holm_max": 0.875,
       "significant_both": false,
       "plain_greater_both": false
      },
      "mistral-small3.2:24b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 125,
         "plain_only": 0,
         "abstain_only": 4,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.031007751937984496
        },
        {
         "n_pairs": 129,
         "n_ties": 125,
         "plain_only": 0,
         "abstain_only": 4,
         "p": 0.125,
         "p_holm": 1.0,
         "plain_rate": 0.0,
         "abstain_rate": 0.031007751937984496
        }
       ],
       "p_holm_max": 1.0,
       "significant_both": false,
       "plain_greater_both": false
      },
      "phi4:14b": {
       "runs": [
        {
         "n_pairs": 129,
         "n_ties": 116,
         "plain_only": 0,
         "abstain_only": 13,
         "p": 0.000244140625,
         "p_holm": 0.00390625,
         "plain_rate": 0.0,
         "abstain_rate": 0.10077519379844961
        },
        {
         "n_pairs": 129,
         "n_ties": 116,
         "plain_only": 0,
         "abstain_only": 13,
         "p": 0.000244140625,
         "p_holm": 0.003662109375,
         "plain_rate": 0.0,
         "abstain_rate": 0.10077519379844961
        }
       ],
       "p_holm_max": 0.00390625,
       "significant_both": true,
       "plain_greater_both": false
      }
     },
     "n_significant_both": 1
    }
   },
   "tradeoff": {
    "qwen3:8b": {
     "drop": [
      70.54263565891473,
      68.9922480620155
     ],
     "rise": [
      2.3255813953488373,
      2.3255813953488373
     ],
     "correct_change": [
      -3.10077519379845,
      -2.3255813953488373
     ],
     "disp": {
      "drop": "69.0〜70.5",
      "rise": "2.3",
      "correct_change": "-3.1〜-2.3",
      "drop0": "69〜71",
      "rise0": "2"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "qwen3:14b": {
     "drop": [
      57.36434108527132,
      60.46511627906977
     ],
     "rise": [
      1.550387596899225,
      1.550387596899225
     ],
     "correct_change": [
      -0.7751937984496124,
      -0.7751937984496124
     ],
     "disp": {
      "drop": "57.4〜60.5",
      "rise": "1.6",
      "correct_change": "-0.8",
      "drop0": "57〜60",
      "rise0": "2"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "qwen3:30b": {
     "drop": [
      45.736434108527135,
      40.310077519379846
     ],
     "rise": [
      1.550387596899225,
      0.7751937984496124
     ],
     "correct_change": [
      1.550387596899225,
      0.0
     ],
     "disp": {
      "drop": "40.3〜45.7",
      "rise": "0.8〜1.6",
      "correct_change": "0.0〜1.6",
      "drop0": "40〜46",
      "rise0": "1〜2"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "qwen3.5:9b": {
     "drop": [
      28.68217054263566,
      29.45736434108527
     ],
     "rise": [
      3.875968992248062,
      3.875968992248062
     ],
     "correct_change": [
      -1.550387596899225,
      -2.3255813953488373
     ],
     "disp": {
      "drop": "28.7〜29.5",
      "rise": "3.9",
      "correct_change": "-2.3〜-1.6",
      "drop0": "29",
      "rise0": "4"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "qwen3.5:27b": {
     "drop": [
      17.05426356589147,
      17.05426356589147
     ],
     "rise": [
      2.3255813953488373,
      2.3255813953488373
     ],
     "correct_change": [
      -2.3255813953488373,
      -2.3255813953488373
     ],
     "disp": {
      "drop": "17.1",
      "rise": "2.3",
      "correct_change": "-2.3",
      "drop0": "17",
      "rise0": "2"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "gemma3:12b": {
     "drop": [
      23.25581395348837,
      20.930232558139537
     ],
     "rise": [
      1.550387596899225,
      1.550387596899225
     ],
     "correct_change": [
      -2.3255813953488373,
      -1.550387596899225
     ],
     "disp": {
      "drop": "20.9〜23.3",
      "rise": "1.6",
      "correct_change": "-2.3〜-1.6",
      "drop0": "21〜23",
      "rise0": "2"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "gemma3:27b": {
     "drop": [
      28.68217054263566,
      27.906976744186046
     ],
     "rise": [
      1.550387596899225,
      1.550387596899225
     ],
     "correct_change": [
      0.0,
      0.0
     ],
     "disp": {
      "drop": "27.9〜28.7",
      "rise": "1.6",
      "correct_change": "0.0",
      "drop0": "28〜29",
      "rise0": "2"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "gemma4:12b": {
     "drop": [
      20.930232558139537,
      20.155038759689923
     ],
     "rise": [
      3.875968992248062,
      3.10077519379845
     ],
     "correct_change": [
      -3.10077519379845,
      -2.3255813953488373
     ],
     "disp": {
      "drop": "20.2〜20.9",
      "rise": "3.1〜3.9",
      "correct_change": "-3.1〜-2.3",
      "drop0": "20〜21",
      "rise0": "3〜4"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "gemma4:26b": {
     "drop": [
      13.953488372093023,
      10.852713178294573
     ],
     "rise": [
      0.7751937984496124,
      1.550387596899225
     ],
     "correct_change": [
      -0.7751937984496124,
      -1.550387596899225
     ],
     "disp": {
      "drop": "10.9〜14.0",
      "rise": "0.8〜1.6",
      "correct_change": "-1.6〜-0.8",
      "drop0": "11〜14",
      "rise0": "1〜2"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "gpt-oss:20b": {
     "drop": [
      55.81395348837209,
      58.91472868217054
     ],
     "rise": [
      0.7751937984496124,
      0.0
     ],
     "correct_change": [
      -1.550387596899225,
      -1.550387596899225
     ],
     "disp": {
      "drop": "55.8〜58.9",
      "rise": "0.0〜0.8",
      "correct_change": "-1.6",
      "drop0": "56〜59",
      "rise0": "0〜1"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": false,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "gpt-oss:120b": {
     "drop": [
      66.66666666666667,
      65.89147286821705
     ],
     "rise": [
      1.550387596899225,
      1.550387596899225
     ],
     "correct_change": [
      -0.7751937984496124,
      0.0
     ],
     "disp": {
      "drop": "65.9〜66.7",
      "rise": "1.6",
      "correct_change": "-0.8〜0.0",
      "drop0": "66〜67",
      "rise0": "2"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "deepseek-r1:8b": {
     "drop": [
      25.58139534883721,
      27.131782945736433
     ],
     "rise": [
      6.976744186046512,
      11.627906976744185
     ],
     "correct_change": [
      0.7751937984496124,
      -6.976744186046512
     ],
     "disp": {
      "drop": "25.6〜27.1",
      "rise": "7.0〜11.6",
      "correct_change": "-7.0〜0.8",
      "drop0": "26〜27",
      "rise0": "7〜12"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "deepseek-r1:14b": {
     "drop": [
      40.310077519379846,
      40.310077519379846
     ],
     "rise": [
      3.875968992248062,
      3.10077519379845
     ],
     "correct_change": [
      -1.550387596899225,
      0.7751937984496124
     ],
     "disp": {
      "drop": "40.3",
      "rise": "3.1〜3.9",
      "correct_change": "-1.6〜0.8",
      "drop0": "40",
      "rise0": "3〜4"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "llama3.1:8b": {
     "drop": [
      64.34108527131782,
      65.11627906976744
     ],
     "rise": [
      3.875968992248062,
      3.875968992248062
     ],
     "correct_change": [
      -10.852713178294573,
      -12.4031007751938
     ],
     "disp": {
      "drop": "64.3〜65.1",
      "rise": "3.9",
      "correct_change": "-12.4〜-10.9",
      "drop0": "64〜65",
      "rise0": "4"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "mistral-small3.2:24b": {
     "drop": [
      43.41085271317829,
      44.96124031007752
     ],
     "rise": [
      3.10077519379845,
      3.10077519379845
     ],
     "correct_change": [
      -1.550387596899225,
      -1.550387596899225
     ],
     "disp": {
      "drop": "43.4〜45.0",
      "rise": "3.1",
      "correct_change": "-1.6",
      "drop0": "43〜45",
      "rise0": "3"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": false
    },
    "phi4:14b": {
     "drop": [
      31.007751937984494,
      29.45736434108527
     ],
     "rise": [
      10.077519379844961,
      10.077519379844961
     ],
     "correct_change": [
      -8.527131782945736,
      -9.30232558139535
     ],
     "disp": {
      "drop": "29.5〜31.0",
      "rise": "10.1",
      "correct_change": "-9.3〜-8.5",
      "drop0": "29〜31",
      "rise0": "10"
     },
     "drop_both_runs_positive": true,
     "rise_both_runs_positive": true,
     "drop_significant_both": true,
     "rise_significant_both": true
    }
   },
   "order_by_near_plain": [
    "qwen3:8b",
    "gpt-oss:20b",
    "llama3.1:8b",
    "gpt-oss:120b",
    "qwen3:14b",
    "qwen3:30b",
    "mistral-small3.2:24b",
    "deepseek-r1:14b",
    "gemma3:27b",
    "qwen3.5:9b",
    "deepseek-r1:8b",
    "gemma3:12b",
    "phi4:14b",
    "gemma4:12b",
    "gemma4:26b",
    "qwen3.5:27b"
   ]
  }
 },
 "exclusion_effect": {
  "models": {
   "qwen3:8b": {
    "near_plain_answered": {
     "all": [
      0.8333333333333334,
      0.8154761904761905
     ],
     "excluded": [
      0.8527131782945736,
      0.8372093023255814
     ]
    },
    "drop": {
     "all": [
      64.28571428571429,
      62.5
     ],
     "excluded": [
      70.54263565891473,
      68.9922480620155
     ]
    },
    "rise": {
     "all": [
      2.380952380952381,
      2.380952380952381
     ],
     "excluded": [
      2.3255813953488373,
      2.3255813953488373
     ]
    },
    "same_direction": true
   },
   "qwen3:14b": {
    "near_plain_answered": {
     "all": [
      0.6904761904761905,
      0.7202380952380952
     ],
     "excluded": [
      0.7131782945736435,
      0.7441860465116279
     ]
    },
    "drop": {
     "all": [
      52.38095238095238,
      55.357142857142854
     ],
     "excluded": [
      57.36434108527132,
      60.46511627906977
     ]
    },
    "rise": {
     "all": [
      1.1904761904761905,
      1.1904761904761905
     ],
     "excluded": [
      1.550387596899225,
      1.550387596899225
     ]
    },
    "same_direction": true
   },
   "qwen3:30b": {
    "near_plain_answered": {
     "all": [
      0.6369047619047619,
      0.6011904761904762
     ],
     "excluded": [
      0.627906976744186,
      0.5813953488372093
     ]
    },
    "drop": {
     "all": [
      42.857142857142854,
      38.69047619047619
     ],
     "excluded": [
      45.736434108527135,
      40.310077519379846
     ]
    },
    "rise": {
     "all": [
      1.1904761904761905,
      0.5952380952380952
     ],
     "excluded": [
      1.550387596899225,
      0.7751937984496124
     ]
    },
    "same_direction": true
   },
   "qwen3.5:9b": {
    "near_plain_answered": {
     "all": [
      0.39285714285714285,
      0.39880952380952384
     ],
     "excluded": [
      0.37209302325581395,
      0.3798449612403101
     ]
    },
    "drop": {
     "all": [
      27.976190476190474,
      29.166666666666668
     ],
     "excluded": [
      28.68217054263566,
      29.45736434108527
     ]
    },
    "rise": {
     "all": [
      3.5714285714285716,
      3.5714285714285716
     ],
     "excluded": [
      3.875968992248062,
      3.875968992248062
     ]
    },
    "same_direction": true
   },
   "qwen3.5:27b": {
    "near_plain_answered": {
     "all": [
      0.23809523809523808,
      0.23809523809523808
     ],
     "excluded": [
      0.17829457364341086,
      0.17829457364341086
     ]
    },
    "drop": {
     "all": [
      19.642857142857142,
      19.642857142857142
     ],
     "excluded": [
      17.05426356589147,
      17.05426356589147
     ]
    },
    "rise": {
     "all": [
      1.7857142857142858,
      2.380952380952381
     ],
     "excluded": [
      2.3255813953488373,
      2.3255813953488373
     ]
    },
    "same_direction": true
   },
   "gemma3:12b": {
    "near_plain_answered": {
     "all": [
      0.4107142857142857,
      0.39880952380952384
     ],
     "excluded": [
      0.3643410852713178,
      0.3488372093023256
     ]
    },
    "drop": {
     "all": [
      23.80952380952381,
      22.023809523809526
     ],
     "excluded": [
      23.25581395348837,
      20.930232558139537
     ]
    },
    "rise": {
     "all": [
      2.380952380952381,
      2.380952380952381
     ],
     "excluded": [
      1.550387596899225,
      1.550387596899225
     ]
    },
    "same_direction": true
   },
   "gemma3:27b": {
    "near_plain_answered": {
     "all": [
      0.49404761904761907,
      0.48214285714285715
     ],
     "excluded": [
      0.4728682170542636,
      0.4573643410852713
     ]
    },
    "drop": {
     "all": [
      28.571428571428573,
      27.38095238095238
     ],
     "excluded": [
      28.68217054263566,
      27.906976744186046
     ]
    },
    "rise": {
     "all": [
      1.1904761904761905,
      1.1904761904761905
     ],
     "excluded": [
      1.550387596899225,
      1.550387596899225
     ]
    },
    "same_direction": true
   },
   "gemma4:12b": {
    "near_plain_answered": {
     "all": [
      0.35119047619047616,
      0.35119047619047616
     ],
     "excluded": [
      0.2868217054263566,
      0.2868217054263566
     ]
    },
    "drop": {
     "all": [
      23.214285714285715,
      22.61904761904762
     ],
     "excluded": [
      20.930232558139537,
      20.155038759689923
     ]
    },
    "rise": {
     "all": [
      2.9761904761904763,
      2.380952380952381
     ],
     "excluded": [
      3.875968992248062,
      3.10077519379845
     ]
    },
    "same_direction": true
   },
   "gemma4:26b": {
    "near_plain_answered": {
     "all": [
      0.25,
      0.23214285714285715
     ],
     "excluded": [
      0.21705426356589147,
      0.1937984496124031
     ]
    },
    "drop": {
     "all": [
      13.69047619047619,
      11.30952380952381
     ],
     "excluded": [
      13.953488372093023,
      10.852713178294573
     ]
    },
    "rise": {
     "all": [
      0.5952380952380952,
      1.1904761904761905
     ],
     "excluded": [
      0.7751937984496124,
      1.550387596899225
     ]
    },
    "same_direction": true
   },
   "gpt-oss:20b": {
    "near_plain_answered": {
     "all": [
      0.7976190476190477,
      0.8214285714285714
     ],
     "excluded": [
      0.7906976744186046,
      0.813953488372093
     ]
    },
    "drop": {
     "all": [
      52.38095238095238,
      54.76190476190476
     ],
     "excluded": [
      55.81395348837209,
      58.91472868217054
     ]
    },
    "rise": {
     "all": [
      0.5952380952380952,
      0.0
     ],
     "excluded": [
      0.7751937984496124,
      0.0
     ]
    },
    "same_direction": true
   },
   "gpt-oss:120b": {
    "near_plain_answered": {
     "all": [
      0.7142857142857143,
      0.7321428571428571
     ],
     "excluded": [
      0.7364341085271318,
      0.7286821705426356
     ]
    },
    "drop": {
     "all": [
      62.5,
      63.69047619047619
     ],
     "excluded": [
      66.66666666666667,
      65.89147286821705
     ]
    },
    "rise": {
     "all": [
      1.1904761904761905,
      1.1904761904761905
     ],
     "excluded": [
      1.550387596899225,
      1.550387596899225
     ]
    },
    "same_direction": true
   },
   "deepseek-r1:8b": {
    "near_plain_answered": {
     "all": [
      0.4226190476190476,
      0.4107142857142857
     ],
     "excluded": [
      0.3798449612403101,
      0.37209302325581395
     ]
    },
    "drop": {
     "all": [
      27.38095238095238,
      27.38095238095238
     ],
     "excluded": [
      25.58139534883721,
      27.131782945736433
     ]
    },
    "rise": {
     "all": [
      6.5476190476190474,
      10.714285714285714
     ],
     "excluded": [
      6.976744186046512,
      11.627906976744185
     ]
    },
    "same_direction": true
   },
   "deepseek-r1:14b": {
    "near_plain_answered": {
     "all": [
      0.5476190476190477,
      0.5357142857142857
     ],
     "excluded": [
      0.5038759689922481,
      0.49612403100775193
     ]
    },
    "drop": {
     "all": [
      39.88095238095238,
      38.69047619047619
     ],
     "excluded": [
      40.310077519379846,
      40.310077519379846
     ]
    },
    "rise": {
     "all": [
      3.5714285714285716,
      2.9761904761904763
     ],
     "excluded": [
      3.875968992248062,
      3.10077519379845
     ]
    },
    "same_direction": true
   },
   "llama3.1:8b": {
    "near_plain_answered": {
     "all": [
      0.8035714285714286,
      0.8035714285714286
     ],
     "excluded": [
      0.7906976744186046,
      0.7984496124031008
     ]
    },
    "drop": {
     "all": [
      63.69047619047619,
      64.28571428571429
     ],
     "excluded": [
      64.34108527131782,
      65.11627906976744
     ]
    },
    "rise": {
     "all": [
      4.761904761904762,
      4.761904761904762
     ],
     "excluded": [
      3.875968992248062,
      3.875968992248062
     ]
    },
    "same_direction": true
   },
   "mistral-small3.2:24b": {
    "near_plain_answered": {
     "all": [
      0.5952380952380952,
      0.6071428571428571
     ],
     "excluded": [
      0.5426356589147286,
      0.5581395348837209
     ]
    },
    "drop": {
     "all": [
      42.857142857142854,
      44.04761904761905
     ],
     "excluded": [
      43.41085271317829,
      44.96124031007752
     ]
    },
    "rise": {
     "all": [
      2.380952380952381,
      2.380952380952381
     ],
     "excluded": [
      3.10077519379845,
      3.10077519379845
     ]
    },
    "same_direction": true
   },
   "phi4:14b": {
    "near_plain_answered": {
     "all": [
      0.40476190476190477,
      0.39285714285714285
     ],
     "excluded": [
      0.3643410852713178,
      0.3488372093023256
     ]
    },
    "drop": {
     "all": [
      33.333333333333336,
      32.142857142857146
     ],
     "excluded": [
      31.007751937984494,
      29.45736434108527
     ]
    },
    "rise": {
     "all": [
      9.523809523809524,
      9.523809523809524
     ],
     "excluded": [
      10.077519379844961,
      10.077519379844961
     ]
    },
    "same_direction": true
   }
  },
  "all_same_direction": true
 },
 "number_source": {
  "all": {
   "cells": {
    "qwen3:8b": {
     "plain": {
      "in_doc": [
       61,
       59
      ],
      "not_in_doc": [
       19,
       20
      ],
      "no_number": [
       2,
       2
      ],
      "multiple_all_in_doc": [
       10,
       10
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       6,
       5
      ],
      "multiple": [
       16,
       15
      ],
      "unsplittable": [
       18,
       17
      ],
      "number_rows": [
       98,
       96
      ],
      "answered_rows": [
       140,
       137
      ],
      "disp": {
       "in_doc": "59〜61",
       "not_in_doc": "19〜20",
       "unsplittable": "17〜18",
       "number_rows": "96〜98",
       "answered_rows": "137〜140"
      }
     },
     "abstain": {
      "in_doc": [
       11,
       11
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       3,
       3
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       2,
       2
      ],
      "multiple": [
       5,
       5
      ],
      "unsplittable": [
       5,
       5
      ],
      "number_rows": [
       16,
       16
      ],
      "answered_rows": [
       32,
       32
      ],
      "disp": {
       "in_doc": "11",
       "not_in_doc": "0",
       "unsplittable": "5",
       "number_rows": "16",
       "answered_rows": "32"
      }
     },
     "quote": {
      "in_doc": [
       10,
       10
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       1
      ],
      "multiple_all_in_doc": [
       4,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       3,
       3
      ],
      "multiple": [
       7,
       7
      ],
      "unsplittable": [
       7,
       8
      ],
      "number_rows": [
       17,
       18
      ],
      "answered_rows": [
       23,
       24
      ],
      "disp": {
       "in_doc": "10",
       "not_in_doc": "0",
       "unsplittable": "7〜8",
       "number_rows": "17〜18",
       "answered_rows": "23〜24"
      }
     }
    },
    "qwen3:14b": {
     "plain": {
      "in_doc": [
       48,
       49
      ],
      "not_in_doc": [
       14,
       15
      ],
      "no_number": [
       2,
       2
      ],
      "multiple_all_in_doc": [
       13,
       14
      ],
      "multiple_none_in_doc": [
       1,
       1
      ],
      "multiple_mixed": [
       2,
       2
      ],
      "multiple": [
       16,
       17
      ],
      "unsplittable": [
       18,
       19
      ],
      "number_rows": [
       80,
       83
      ],
      "answered_rows": [
       116,
       121
      ],
      "disp": {
       "in_doc": "48〜49",
       "not_in_doc": "14〜15",
       "unsplittable": "18〜19",
       "number_rows": "80〜83",
       "answered_rows": "116〜121"
      }
     },
     "abstain": {
      "in_doc": [
       10,
       10
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       6,
       6
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       6,
       6
      ],
      "unsplittable": [
       6,
       6
      ],
      "number_rows": [
       16,
       16
      ],
      "answered_rows": [
       28,
       28
      ],
      "disp": {
       "in_doc": "10",
       "not_in_doc": "0",
       "unsplittable": "6",
       "number_rows": "16",
       "answered_rows": "28"
      }
     },
     "quote": {
      "in_doc": [
       20,
       19
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       7,
       7
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       1,
       1
      ],
      "multiple": [
       8,
       8
      ],
      "unsplittable": [
       9,
       9
      ],
      "number_rows": [
       30,
       29
      ],
      "answered_rows": [
       49,
       48
      ],
      "disp": {
       "in_doc": "19〜20",
       "not_in_doc": "1",
       "unsplittable": "9",
       "number_rows": "29〜30",
       "answered_rows": "48〜49"
      }
     }
    },
    "qwen3:30b": {
     "plain": {
      "in_doc": [
       45,
       35
      ],
      "not_in_doc": [
       15,
       16
      ],
      "no_number": [
       4,
       5
      ],
      "multiple_all_in_doc": [
       6,
       6
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       6,
       6
      ],
      "unsplittable": [
       10,
       11
      ],
      "number_rows": [
       70,
       62
      ],
      "answered_rows": [
       107,
       101
      ],
      "disp": {
       "in_doc": "35〜45",
       "not_in_doc": "15〜16",
       "unsplittable": "10〜11",
       "number_rows": "62〜70",
       "answered_rows": "101〜107"
      }
     },
     "abstain": {
      "in_doc": [
       15,
       21
      ],
      "not_in_doc": [
       3,
       1
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       3,
       3
      ],
      "multiple_none_in_doc": [
       1,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       4,
       3
      ],
      "unsplittable": [
       4,
       3
      ],
      "number_rows": [
       22,
       25
      ],
      "answered_rows": [
       35,
       36
      ],
      "disp": {
       "in_doc": "15〜21",
       "not_in_doc": "1〜3",
       "unsplittable": "3〜4",
       "number_rows": "22〜25",
       "answered_rows": "35〜36"
      }
     },
     "quote": {
      "in_doc": [
       13,
       13
      ],
      "not_in_doc": [
       3,
       1
      ],
      "no_number": [
       0,
       1
      ],
      "multiple_all_in_doc": [
       4,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       4,
       4
      ],
      "unsplittable": [
       4,
       5
      ],
      "number_rows": [
       20,
       19
      ],
      "answered_rows": [
       32,
       30
      ],
      "disp": {
       "in_doc": "13",
       "not_in_doc": "1〜3",
       "unsplittable": "4〜5",
       "number_rows": "19〜20",
       "answered_rows": "30〜32"
      }
     }
    },
    "qwen3.5:9b": {
     "plain": {
      "in_doc": [
       31,
       31
      ],
      "not_in_doc": [
       4,
       5
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       8,
       8
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       8,
       8
      ],
      "unsplittable": [
       9,
       9
      ],
      "number_rows": [
       44,
       45
      ],
      "answered_rows": [
       66,
       67
      ],
      "disp": {
       "in_doc": "31",
       "not_in_doc": "4〜5",
       "unsplittable": "9",
       "number_rows": "44〜45",
       "answered_rows": "66〜67"
      }
     },
     "abstain": {
      "in_doc": [
       10,
       10
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       3,
       3
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       3,
       3
      ],
      "unsplittable": [
       3,
       3
      ],
      "number_rows": [
       14,
       14
      ],
      "answered_rows": [
       19,
       18
      ],
      "disp": {
       "in_doc": "10",
       "not_in_doc": "1",
       "unsplittable": "3",
       "number_rows": "14",
       "answered_rows": "18〜19"
      }
     },
     "quote": {
      "in_doc": [
       1,
       1
      ],
      "not_in_doc": [
       0,
       1
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       2,
       2
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       2,
       1
      ],
      "multiple": [
       4,
       3
      ],
      "unsplittable": [
       4,
       3
      ],
      "number_rows": [
       5,
       5
      ],
      "answered_rows": [
       7,
       7
      ],
      "disp": {
       "in_doc": "1",
       "not_in_doc": "0〜1",
       "unsplittable": "3〜4",
       "number_rows": "5",
       "answered_rows": "7"
      }
     }
    },
    "qwen3.5:27b": {
     "plain": {
      "in_doc": [
       14,
       13
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       6,
       7
      ],
      "multiple_none_in_doc": [
       1,
       1
      ],
      "multiple_mixed": [
       1,
       1
      ],
      "multiple": [
       8,
       9
      ],
      "unsplittable": [
       8,
       9
      ],
      "number_rows": [
       23,
       23
      ],
      "answered_rows": [
       40,
       40
      ],
      "disp": {
       "in_doc": "13〜14",
       "not_in_doc": "1",
       "unsplittable": "8〜9",
       "number_rows": "23",
       "answered_rows": "40"
      }
     },
     "abstain": {
      "in_doc": [
       3,
       3
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       1,
       1
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       1,
       1
      ],
      "unsplittable": [
       1,
       1
      ],
      "number_rows": [
       4,
       4
      ],
      "answered_rows": [
       7,
       7
      ],
      "disp": {
       "in_doc": "3",
       "not_in_doc": "0",
       "unsplittable": "1",
       "number_rows": "4",
       "answered_rows": "7"
      }
     },
     "quote": {
      "in_doc": [
       3,
       3
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       0,
       0
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       0,
       0
      ],
      "unsplittable": [
       0,
       0
      ],
      "number_rows": [
       3,
       3
      ],
      "answered_rows": [
       9,
       10
      ],
      "disp": {
       "in_doc": "3",
       "not_in_doc": "0",
       "unsplittable": "0",
       "number_rows": "3",
       "answered_rows": "9〜10"
      }
     }
    },
    "gemma3:12b": {
     "plain": {
      "in_doc": [
       24,
       24
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       4,
       4
      ],
      "multiple_all_in_doc": [
       8,
       7
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       8,
       7
      ],
      "unsplittable": [
       12,
       11
      ],
      "number_rows": [
       37,
       36
      ],
      "answered_rows": [
       69,
       67
      ],
      "disp": {
       "in_doc": "24",
       "not_in_doc": "1",
       "unsplittable": "11〜12",
       "number_rows": "36〜37",
       "answered_rows": "67〜69"
      }
     },
     "abstain": {
      "in_doc": [
       8,
       8
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       4,
       5
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       4,
       5
      ],
      "unsplittable": [
       5,
       6
      ],
      "number_rows": [
       13,
       14
      ],
      "answered_rows": [
       29,
       30
      ],
      "disp": {
       "in_doc": "8",
       "not_in_doc": "0",
       "unsplittable": "5〜6",
       "number_rows": "13〜14",
       "answered_rows": "29〜30"
      }
     },
     "quote": {
      "in_doc": [
       2,
       2
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       9,
       9
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       9,
       9
      ],
      "unsplittable": [
       10,
       10
      ],
      "number_rows": [
       12,
       12
      ],
      "answered_rows": [
       23,
       23
      ],
      "disp": {
       "in_doc": "2",
       "not_in_doc": "0",
       "unsplittable": "10",
       "number_rows": "12",
       "answered_rows": "23"
      }
     }
    },
    "gemma3:27b": {
     "plain": {
      "in_doc": [
       38,
       38
      ],
      "not_in_doc": [
       6,
       5
      ],
      "no_number": [
       2,
       2
      ],
      "multiple_all_in_doc": [
       8,
       8
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       8,
       8
      ],
      "unsplittable": [
       10,
       10
      ],
      "number_rows": [
       54,
       53
      ],
      "answered_rows": [
       83,
       81
      ],
      "disp": {
       "in_doc": "38",
       "not_in_doc": "5〜6",
       "unsplittable": "10",
       "number_rows": "53〜54",
       "answered_rows": "81〜83"
      }
     },
     "abstain": {
      "in_doc": [
       14,
       14
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       5,
       5
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       5,
       5
      ],
      "unsplittable": [
       6,
       6
      ],
      "number_rows": [
       21,
       21
      ],
      "answered_rows": [
       35,
       35
      ],
      "disp": {
       "in_doc": "14",
       "not_in_doc": "1",
       "unsplittable": "6",
       "number_rows": "21",
       "answered_rows": "35"
      }
     },
     "quote": {
      "in_doc": [
       16,
       15
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       1,
       0
      ],
      "multiple_all_in_doc": [
       7,
       8
      ],
      "multiple_none_in_doc": [
       1,
       0
      ],
      "multiple_mixed": [
       2,
       2
      ],
      "multiple": [
       10,
       10
      ],
      "unsplittable": [
       11,
       10
      ],
      "number_rows": [
       28,
       26
      ],
      "answered_rows": [
       44,
       42
      ],
      "disp": {
       "in_doc": "15〜16",
       "not_in_doc": "1",
       "unsplittable": "10〜11",
       "number_rows": "26〜28",
       "answered_rows": "42〜44"
      }
     }
    },
    "gemma4:12b": {
     "plain": {
      "in_doc": [
       26,
       25
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       9,
       9
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       9,
       9
      ],
      "unsplittable": [
       10,
       10
      ],
      "number_rows": [
       36,
       35
      ],
      "answered_rows": [
       59,
       59
      ],
      "disp": {
       "in_doc": "25〜26",
       "not_in_doc": "0",
       "unsplittable": "10",
       "number_rows": "35〜36",
       "answered_rows": "59"
      }
     },
     "abstain": {
      "in_doc": [
       8,
       9
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       5,
       5
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       5,
       5
      ],
      "unsplittable": [
       5,
       5
      ],
      "number_rows": [
       14,
       15
      ],
      "answered_rows": [
       20,
       21
      ],
      "disp": {
       "in_doc": "8〜9",
       "not_in_doc": "1",
       "unsplittable": "5",
       "number_rows": "14〜15",
       "answered_rows": "20〜21"
      }
     },
     "quote": {
      "in_doc": [
       4,
       4
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       3,
       3
      ],
      "multiple_all_in_doc": [
       8,
       8
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       1,
       1
      ],
      "multiple": [
       9,
       9
      ],
      "unsplittable": [
       12,
       12
      ],
      "number_rows": [
       16,
       16
      ],
      "answered_rows": [
       25,
       24
      ],
      "disp": {
       "in_doc": "4",
       "not_in_doc": "0",
       "unsplittable": "12",
       "number_rows": "16",
       "answered_rows": "24〜25"
      }
     }
    },
    "gemma4:26b": {
     "plain": {
      "in_doc": [
       18,
       15
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       5,
       5
      ],
      "multiple_none_in_doc": [
       1,
       0
      ],
      "multiple_mixed": [
       1,
       2
      ],
      "multiple": [
       7,
       7
      ],
      "unsplittable": [
       8,
       8
      ],
      "number_rows": [
       27,
       24
      ],
      "answered_rows": [
       42,
       39
      ],
      "disp": {
       "in_doc": "15〜18",
       "not_in_doc": "1",
       "unsplittable": "8",
       "number_rows": "24〜27",
       "answered_rows": "39〜42"
      }
     },
     "abstain": {
      "in_doc": [
       8,
       9
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       4,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       4,
       4
      ],
      "unsplittable": [
       4,
       4
      ],
      "number_rows": [
       13,
       14
      ],
      "answered_rows": [
       19,
       20
      ],
      "disp": {
       "in_doc": "8〜9",
       "not_in_doc": "1",
       "unsplittable": "4",
       "number_rows": "13〜14",
       "answered_rows": "19〜20"
      }
     },
     "quote": {
      "in_doc": [
       5,
       5
      ],
      "not_in_doc": [
       2,
       2
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       3,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       3,
       4
      ],
      "unsplittable": [
       4,
       5
      ],
      "number_rows": [
       11,
       12
      ],
      "answered_rows": [
       16,
       17
      ],
      "disp": {
       "in_doc": "5",
       "not_in_doc": "2",
       "unsplittable": "4〜5",
       "number_rows": "11〜12",
       "answered_rows": "16〜17"
      }
     }
    },
    "gpt-oss:20b": {
     "plain": {
      "in_doc": [
       43,
       44
      ],
      "not_in_doc": [
       32,
       31
      ],
      "no_number": [
       2,
       2
      ],
      "multiple_all_in_doc": [
       8,
       12
      ],
      "multiple_none_in_doc": [
       3,
       1
      ],
      "multiple_mixed": [
       2,
       2
      ],
      "multiple": [
       13,
       15
      ],
      "unsplittable": [
       15,
       17
      ],
      "number_rows": [
       90,
       92
      ],
      "answered_rows": [
       134,
       138
      ],
      "disp": {
       "in_doc": "43〜44",
       "not_in_doc": "31〜32",
       "unsplittable": "15〜17",
       "number_rows": "90〜92",
       "answered_rows": "134〜138"
      }
     },
     "abstain": {
      "in_doc": [
       18,
       19
      ],
      "not_in_doc": [
       4,
       3
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       5,
       6
      ],
      "multiple_none_in_doc": [
       1,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       6,
       6
      ],
      "unsplittable": [
       6,
       6
      ],
      "number_rows": [
       28,
       28
      ],
      "answered_rows": [
       46,
       46
      ],
      "disp": {
       "in_doc": "18〜19",
       "not_in_doc": "3〜4",
       "unsplittable": "6",
       "number_rows": "28",
       "answered_rows": "46"
      }
     },
     "quote": {
      "in_doc": [
       13,
       16
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       10,
       9
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       5,
       2
      ],
      "multiple": [
       15,
       11
      ],
      "unsplittable": [
       16,
       12
      ],
      "number_rows": [
       30,
       29
      ],
      "answered_rows": [
       46,
       45
      ],
      "disp": {
       "in_doc": "13〜16",
       "not_in_doc": "1",
       "unsplittable": "12〜16",
       "number_rows": "29〜30",
       "answered_rows": "45〜46"
      }
     }
    },
    "gpt-oss:120b": {
     "plain": {
      "in_doc": [
       47,
       42
      ],
      "not_in_doc": [
       30,
       33
      ],
      "no_number": [
       0,
       1
      ],
      "multiple_all_in_doc": [
       3,
       6
      ],
      "multiple_none_in_doc": [
       1,
       2
      ],
      "multiple_mixed": [
       2,
       1
      ],
      "multiple": [
       6,
       9
      ],
      "unsplittable": [
       6,
       10
      ],
      "number_rows": [
       83,
       85
      ],
      "answered_rows": [
       120,
       123
      ],
      "disp": {
       "in_doc": "42〜47",
       "not_in_doc": "30〜33",
       "unsplittable": "6〜10",
       "number_rows": "83〜85",
       "answered_rows": "120〜123"
      }
     },
     "abstain": {
      "in_doc": [
       8,
       7
      ],
      "not_in_doc": [
       1,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       2,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       2,
       4
      ],
      "unsplittable": [
       2,
       4
      ],
      "number_rows": [
       11,
       11
      ],
      "answered_rows": [
       15,
       16
      ],
      "disp": {
       "in_doc": "7〜8",
       "not_in_doc": "0〜1",
       "unsplittable": "2〜4",
       "number_rows": "11",
       "answered_rows": "15〜16"
      }
     },
     "quote": {
      "in_doc": [
       3,
       2
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       6,
       7
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       4,
       2
      ],
      "multiple": [
       10,
       9
      ],
      "unsplittable": [
       10,
       9
      ],
      "number_rows": [
       13,
       11
      ],
      "answered_rows": [
       21,
       17
      ],
      "disp": {
       "in_doc": "2〜3",
       "not_in_doc": "0",
       "unsplittable": "9〜10",
       "number_rows": "11〜13",
       "answered_rows": "17〜21"
      }
     }
    },
    "deepseek-r1:8b": {
     "plain": {
      "in_doc": [
       23,
       21
      ],
      "not_in_doc": [
       10,
       9
      ],
      "no_number": [
       0,
       1
      ],
      "multiple_all_in_doc": [
       9,
       5
      ],
      "multiple_none_in_doc": [
       2,
       1
      ],
      "multiple_mixed": [
       1,
       5
      ],
      "multiple": [
       12,
       11
      ],
      "unsplittable": [
       12,
       12
      ],
      "number_rows": [
       45,
       42
      ],
      "answered_rows": [
       71,
       69
      ],
      "disp": {
       "in_doc": "21〜23",
       "not_in_doc": "9〜10",
       "unsplittable": "12",
       "number_rows": "42〜45",
       "answered_rows": "69〜71"
      }
     },
     "abstain": {
      "in_doc": [
       7,
       7
      ],
      "not_in_doc": [
       4,
       2
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       3,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       3,
       4
      ],
      "unsplittable": [
       3,
       4
      ],
      "number_rows": [
       14,
       13
      ],
      "answered_rows": [
       25,
       23
      ],
      "disp": {
       "in_doc": "7",
       "not_in_doc": "2〜4",
       "unsplittable": "3〜4",
       "number_rows": "13〜14",
       "answered_rows": "23〜25"
      }
     },
     "quote": {
      "in_doc": [
       3,
       2
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       1
      ],
      "multiple_all_in_doc": [
       4,
       6
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       1,
       1
      ],
      "multiple": [
       5,
       7
      ],
      "unsplittable": [
       5,
       8
      ],
      "number_rows": [
       8,
       10
      ],
      "answered_rows": [
       19,
       18
      ],
      "disp": {
       "in_doc": "2〜3",
       "not_in_doc": "0",
       "unsplittable": "5〜8",
       "number_rows": "8〜10",
       "answered_rows": "18〜19"
      }
     }
    },
    "deepseek-r1:14b": {
     "plain": {
      "in_doc": [
       31,
       29
      ],
      "not_in_doc": [
       9,
       9
      ],
      "no_number": [
       2,
       3
      ],
      "multiple_all_in_doc": [
       7,
       10
      ],
      "multiple_none_in_doc": [
       1,
       0
      ],
      "multiple_mixed": [
       5,
       4
      ],
      "multiple": [
       13,
       14
      ],
      "unsplittable": [
       15,
       17
      ],
      "number_rows": [
       55,
       55
      ],
      "answered_rows": [
       92,
       90
      ],
      "disp": {
       "in_doc": "29〜31",
       "not_in_doc": "9",
       "unsplittable": "15〜17",
       "number_rows": "55",
       "answered_rows": "90〜92"
      }
     },
     "abstain": {
      "in_doc": [
       6,
       10
      ],
      "not_in_doc": [
       2,
       2
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       4,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       2,
       0
      ],
      "multiple": [
       6,
       4
      ],
      "unsplittable": [
       6,
       4
      ],
      "number_rows": [
       14,
       16
      ],
      "answered_rows": [
       25,
       25
      ],
      "disp": {
       "in_doc": "6〜10",
       "not_in_doc": "2",
       "unsplittable": "4〜6",
       "number_rows": "14〜16",
       "answered_rows": "25"
      }
     },
     "quote": {
      "in_doc": [
       4,
       6
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       8,
       9
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       2,
       3
      ],
      "multiple": [
       10,
       12
      ],
      "unsplittable": [
       11,
       13
      ],
      "number_rows": [
       15,
       19
      ],
      "answered_rows": [
       29,
       32
      ],
      "disp": {
       "in_doc": "4〜6",
       "not_in_doc": "0",
       "unsplittable": "11〜13",
       "number_rows": "15〜19",
       "answered_rows": "29〜32"
      }
     }
    },
    "llama3.1:8b": {
     "plain": {
      "in_doc": [
       66,
       66
      ],
      "not_in_doc": [
       8,
       7
      ],
      "no_number": [
       4,
       4
      ],
      "multiple_all_in_doc": [
       16,
       17
      ],
      "multiple_none_in_doc": [
       1,
       1
      ],
      "multiple_mixed": [
       3,
       4
      ],
      "multiple": [
       20,
       22
      ],
      "unsplittable": [
       24,
       26
      ],
      "number_rows": [
       98,
       99
      ],
      "answered_rows": [
       135,
       135
      ],
      "disp": {
       "in_doc": "66",
       "not_in_doc": "7〜8",
       "unsplittable": "24〜26",
       "number_rows": "98〜99",
       "answered_rows": "135"
      }
     },
     "abstain": {
      "in_doc": [
       10,
       10
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       11,
       11
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       11,
       11
      ],
      "unsplittable": [
       11,
       11
      ],
      "number_rows": [
       22,
       22
      ],
      "answered_rows": [
       28,
       27
      ],
      "disp": {
       "in_doc": "10",
       "not_in_doc": "1",
       "unsplittable": "11",
       "number_rows": "22",
       "answered_rows": "27〜28"
      }
     },
     "quote": {
      "in_doc": [
       30,
       31
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       12,
       10
      ],
      "multiple_all_in_doc": [
       35,
       30
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       5,
       6
      ],
      "multiple": [
       40,
       36
      ],
      "unsplittable": [
       52,
       46
      ],
      "number_rows": [
       83,
       78
      ],
      "answered_rows": [
       107,
       102
      ],
      "disp": {
       "in_doc": "30〜31",
       "not_in_doc": "1",
       "unsplittable": "46〜52",
       "number_rows": "78〜83",
       "answered_rows": "102〜107"
      }
     }
    },
    "mistral-small3.2:24b": {
     "plain": {
      "in_doc": [
       43,
       46
      ],
      "not_in_doc": [
       4,
       4
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       15,
       14
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       1,
       1
      ],
      "multiple": [
       16,
       15
      ],
      "unsplittable": [
       16,
       15
      ],
      "number_rows": [
       63,
       65
      ],
      "answered_rows": [
       100,
       102
      ],
      "disp": {
       "in_doc": "43〜46",
       "not_in_doc": "4",
       "unsplittable": "15〜16",
       "number_rows": "63〜65",
       "answered_rows": "100〜102"
      }
     },
     "abstain": {
      "in_doc": [
       10,
       10
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       4,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       1,
       1
      ],
      "multiple": [
       5,
       5
      ],
      "unsplittable": [
       5,
       5
      ],
      "number_rows": [
       15,
       15
      ],
      "answered_rows": [
       28,
       28
      ],
      "disp": {
       "in_doc": "10",
       "not_in_doc": "0",
       "unsplittable": "5",
       "number_rows": "15",
       "answered_rows": "28"
      }
     },
     "quote": {
      "in_doc": [
       10,
       9
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       1,
       2
      ],
      "multiple_all_in_doc": [
       6,
       6
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       4,
       4
      ],
      "multiple": [
       10,
       10
      ],
      "unsplittable": [
       11,
       12
      ],
      "number_rows": [
       21,
       21
      ],
      "answered_rows": [
       33,
       33
      ],
      "disp": {
       "in_doc": "9〜10",
       "not_in_doc": "0",
       "unsplittable": "11〜12",
       "number_rows": "21",
       "answered_rows": "33"
      }
     }
    },
    "phi4:14b": {
     "plain": {
      "in_doc": [
       7,
       5
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       21,
       21
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       13,
       13
      ],
      "multiple": [
       34,
       34
      ],
      "unsplittable": [
       34,
       34
      ],
      "number_rows": [
       41,
       39
      ],
      "answered_rows": [
       68,
       66
      ],
      "disp": {
       "in_doc": "5〜7",
       "not_in_doc": "0",
       "unsplittable": "34",
       "number_rows": "39〜41",
       "answered_rows": "66〜68"
      }
     },
     "abstain": {
      "in_doc": [
       1,
       1
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       6,
       6
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       3,
       3
      ],
      "multiple": [
       9,
       9
      ],
      "unsplittable": [
       9,
       9
      ],
      "number_rows": [
       10,
       10
      ],
      "answered_rows": [
       12,
       12
      ],
      "disp": {
       "in_doc": "1",
       "not_in_doc": "0",
       "unsplittable": "9",
       "number_rows": "10",
       "answered_rows": "12"
      }
     },
     "quote": {
      "in_doc": [
       1,
       1
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       6,
       5
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       1,
       1
      ],
      "multiple": [
       7,
       6
      ],
      "unsplittable": [
       7,
       6
      ],
      "number_rows": [
       8,
       7
      ],
      "answered_rows": [
       12,
       11
      ],
      "disp": {
       "in_doc": "1",
       "not_in_doc": "0",
       "unsplittable": "6〜7",
       "number_rows": "7〜8",
       "answered_rows": "11〜12"
      }
     }
    }
   },
   "by_prompt": {
    "plain": {
     "in_doc": [
      565,
      542
     ],
     "not_in_doc": [
      154,
      157
     ],
     "no_number": [
      25,
      29
     ],
     "multiple_all_in_doc": [
      152,
      159
     ],
     "multiple_none_in_doc": [
      11,
      7
     ],
     "multiple_mixed": [
      37,
      40
     ],
     "multiple": [
      200,
      206
     ],
     "unsplittable": [
      225,
      235
     ],
     "number_rows": [
      944,
      934
     ],
     "answered_rows": [
      1442,
      1435
     ],
     "disp": {
      "in_doc": "542〜565",
      "not_in_doc": "154〜157",
      "unsplittable": "225〜235",
      "number_rows": "934〜944",
      "answered_rows": "1,435〜1,442"
     }
    },
    "abstain": {
     "in_doc": [
      147,
      159
     ],
     "not_in_doc": [
      19,
      13
     ],
     "no_number": [
      2,
      2
     ],
     "multiple_all_in_doc": [
      69,
      74
     ],
     "multiple_none_in_doc": [
      2,
      0
     ],
     "multiple_mixed": [
      8,
      6
     ],
     "multiple": [
      79,
      80
     ],
     "unsplittable": [
      81,
      82
     ],
     "number_rows": [
      247,
      254
     ],
     "answered_rows": [
      403,
      404
     ],
     "disp": {
      "in_doc": "147〜159",
      "not_in_doc": "13〜19",
      "unsplittable": "81〜82",
      "number_rows": "247〜254",
      "answered_rows": "403〜404"
     }
    },
    "quote": {
     "in_doc": [
      138,
      139
     ],
     "not_in_doc": [
      9,
      8
     ],
     "no_number": [
      22,
      23
     ],
     "multiple_all_in_doc": [
      119,
      118
     ],
     "multiple_none_in_doc": [
      1,
      0
     ],
     "multiple_mixed": [
      31,
      27
     ],
     "multiple": [
      151,
      145
     ],
     "unsplittable": [
      173,
      168
     ],
     "number_rows": [
      320,
      315
     ],
     "answered_rows": [
      495,
      483
     ],
     "disp": {
      "in_doc": "138〜139",
      "not_in_doc": "8〜9",
      "unsplittable": "168〜173",
      "number_rows": "315〜320",
      "answered_rows": "483〜495"
     }
    }
   },
   "control_far": {
    "cells": {
     "qwen3:8b": {
      "plain": {
       "in_doc": [
        17,
        17
       ],
       "not_in_doc": [
        63,
        62
       ],
       "no_number": [
        2,
        2
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        11,
        11
       ],
       "multiple_mixed": [
        5,
        4
       ],
       "multiple": [
        16,
        15
       ],
       "unsplittable": [
        18,
        17
       ],
       "number_rows": [
        98,
        96
       ],
       "answered_rows": [
        140,
        137
       ],
       "disp": {
        "in_doc": "17",
        "not_in_doc": "62〜63",
        "unsplittable": "17〜18",
        "number_rows": "96〜98",
        "answered_rows": "137〜140"
       }
      },
      "abstain": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        10,
        10
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        3,
        3
       ],
       "multiple_mixed": [
        1,
        1
       ],
       "multiple": [
        5,
        5
       ],
       "unsplittable": [
        5,
        5
       ],
       "number_rows": [
        16,
        16
       ],
       "answered_rows": [
        32,
        32
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "10",
        "unsplittable": "5",
        "number_rows": "16",
        "answered_rows": "32"
       }
      },
      "quote": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        9,
        9
       ],
       "no_number": [
        0,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        3,
        3
       ],
       "multiple_mixed": [
        4,
        4
       ],
       "multiple": [
        7,
        7
       ],
       "unsplittable": [
        7,
        8
       ],
       "number_rows": [
        17,
        18
       ],
       "answered_rows": [
        23,
        24
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "9",
        "unsplittable": "7〜8",
        "number_rows": "17〜18",
        "answered_rows": "23〜24"
       }
      }
     },
     "qwen3:14b": {
      "plain": {
       "in_doc": [
        13,
        13
       ],
       "not_in_doc": [
        49,
        51
       ],
       "no_number": [
        2,
        2
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        11,
        12
       ],
       "multiple_mixed": [
        5,
        5
       ],
       "multiple": [
        16,
        17
       ],
       "unsplittable": [
        18,
        19
       ],
       "number_rows": [
        80,
        83
       ],
       "answered_rows": [
        116,
        121
       ],
       "disp": {
        "in_doc": "13",
        "not_in_doc": "49〜51",
        "unsplittable": "18〜19",
        "number_rows": "80〜83",
        "answered_rows": "116〜121"
       }
      },
      "abstain": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        9,
        9
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        4,
        4
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        6,
        6
       ],
       "unsplittable": [
        6,
        6
       ],
       "number_rows": [
        16,
        16
       ],
       "answered_rows": [
        28,
        28
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "9",
        "unsplittable": "6",
        "number_rows": "16",
        "answered_rows": "28"
       }
      },
      "quote": {
       "in_doc": [
        5,
        4
       ],
       "not_in_doc": [
        16,
        16
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        3,
        3
       ],
       "multiple_mixed": [
        5,
        5
       ],
       "multiple": [
        8,
        8
       ],
       "unsplittable": [
        9,
        9
       ],
       "number_rows": [
        30,
        29
       ],
       "answered_rows": [
        49,
        48
       ],
       "disp": {
        "in_doc": "4〜5",
        "not_in_doc": "16",
        "unsplittable": "9",
        "number_rows": "29〜30",
        "answered_rows": "48〜49"
       }
      }
     },
     "qwen3:30b": {
      "plain": {
       "in_doc": [
        13,
        11
       ],
       "not_in_doc": [
        47,
        40
       ],
       "no_number": [
        4,
        5
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        5,
        4
       ],
       "multiple_mixed": [
        1,
        2
       ],
       "multiple": [
        6,
        6
       ],
       "unsplittable": [
        10,
        11
       ],
       "number_rows": [
        70,
        62
       ],
       "answered_rows": [
        107,
        101
       ],
       "disp": {
        "in_doc": "11〜13",
        "not_in_doc": "40〜47",
        "unsplittable": "10〜11",
        "number_rows": "62〜70",
        "answered_rows": "101〜107"
       }
      },
      "abstain": {
       "in_doc": [
        5,
        5
       ],
       "not_in_doc": [
        13,
        17
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        3,
        2
       ],
       "multiple_mixed": [
        1,
        1
       ],
       "multiple": [
        4,
        3
       ],
       "unsplittable": [
        4,
        3
       ],
       "number_rows": [
        22,
        25
       ],
       "answered_rows": [
        35,
        36
       ],
       "disp": {
        "in_doc": "5",
        "not_in_doc": "13〜17",
        "unsplittable": "3〜4",
        "number_rows": "22〜25",
        "answered_rows": "35〜36"
       }
      },
      "quote": {
       "in_doc": [
        4,
        3
       ],
       "not_in_doc": [
        12,
        11
       ],
       "no_number": [
        0,
        1
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        1,
        1
       ],
       "multiple": [
        4,
        4
       ],
       "unsplittable": [
        4,
        5
       ],
       "number_rows": [
        20,
        19
       ],
       "answered_rows": [
        32,
        30
       ],
       "disp": {
        "in_doc": "3〜4",
        "not_in_doc": "11〜12",
        "unsplittable": "4〜5",
        "number_rows": "19〜20",
        "answered_rows": "30〜32"
       }
      }
     },
     "qwen3.5:9b": {
      "plain": {
       "in_doc": [
        5,
        5
       ],
       "not_in_doc": [
        30,
        31
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        4,
        4
       ],
       "multiple_mixed": [
        4,
        4
       ],
       "multiple": [
        8,
        8
       ],
       "unsplittable": [
        9,
        9
       ],
       "number_rows": [
        44,
        45
       ],
       "answered_rows": [
        66,
        67
       ],
       "disp": {
        "in_doc": "5",
        "not_in_doc": "30〜31",
        "unsplittable": "9",
        "number_rows": "44〜45",
        "answered_rows": "66〜67"
       }
      },
      "abstain": {
       "in_doc": [
        2,
        2
       ],
       "not_in_doc": [
        9,
        9
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        1,
        1
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        3,
        3
       ],
       "unsplittable": [
        3,
        3
       ],
       "number_rows": [
        14,
        14
       ],
       "answered_rows": [
        19,
        18
       ],
       "disp": {
        "in_doc": "2",
        "not_in_doc": "9",
        "unsplittable": "3",
        "number_rows": "14",
        "answered_rows": "18〜19"
       }
      },
      "quote": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        1,
        2
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        3,
        2
       ],
       "multiple_mixed": [
        1,
        1
       ],
       "multiple": [
        4,
        3
       ],
       "unsplittable": [
        4,
        3
       ],
       "number_rows": [
        5,
        5
       ],
       "answered_rows": [
        7,
        7
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "1〜2",
        "unsplittable": "3〜4",
        "number_rows": "5",
        "answered_rows": "7"
       }
      }
     },
     "qwen3.5:27b": {
      "plain": {
       "in_doc": [
        2,
        2
       ],
       "not_in_doc": [
        13,
        12
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        5,
        5
       ],
       "multiple_mixed": [
        3,
        4
       ],
       "multiple": [
        8,
        9
       ],
       "unsplittable": [
        8,
        9
       ],
       "number_rows": [
        23,
        23
       ],
       "answered_rows": [
        40,
        40
       ],
       "disp": {
        "in_doc": "2",
        "not_in_doc": "12〜13",
        "unsplittable": "8〜9",
        "number_rows": "23",
        "answered_rows": "40"
       }
      },
      "abstain": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        3,
        3
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        1,
        1
       ],
       "multiple_mixed": [
        0,
        0
       ],
       "multiple": [
        1,
        1
       ],
       "unsplittable": [
        1,
        1
       ],
       "number_rows": [
        4,
        4
       ],
       "answered_rows": [
        7,
        7
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "3",
        "unsplittable": "1",
        "number_rows": "4",
        "answered_rows": "7"
       }
      },
      "quote": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        2,
        2
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        0,
        0
       ],
       "multiple_mixed": [
        0,
        0
       ],
       "multiple": [
        0,
        0
       ],
       "unsplittable": [
        0,
        0
       ],
       "number_rows": [
        3,
        3
       ],
       "answered_rows": [
        9,
        10
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "2",
        "unsplittable": "0",
        "number_rows": "3",
        "answered_rows": "9〜10"
       }
      }
     },
     "gemma3:12b": {
      "plain": {
       "in_doc": [
        5,
        4
       ],
       "not_in_doc": [
        20,
        21
       ],
       "no_number": [
        4,
        4
       ],
       "multiple_all_in_doc": [
        1,
        0
       ],
       "multiple_none_in_doc": [
        4,
        4
       ],
       "multiple_mixed": [
        3,
        3
       ],
       "multiple": [
        8,
        7
       ],
       "unsplittable": [
        12,
        11
       ],
       "number_rows": [
        37,
        36
       ],
       "answered_rows": [
        69,
        67
       ],
       "disp": {
        "in_doc": "4〜5",
        "not_in_doc": "20〜21",
        "unsplittable": "11〜12",
        "number_rows": "36〜37",
        "answered_rows": "67〜69"
       }
      },
      "abstain": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        7,
        7
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        1,
        2
       ],
       "multiple": [
        4,
        5
       ],
       "unsplittable": [
        5,
        6
       ],
       "number_rows": [
        13,
        14
       ],
       "answered_rows": [
        29,
        30
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "7",
        "unsplittable": "5〜6",
        "number_rows": "13〜14",
        "answered_rows": "29〜30"
       }
      },
      "quote": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        2,
        2
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        2,
        2
       ],
       "multiple_none_in_doc": [
        3,
        3
       ],
       "multiple_mixed": [
        4,
        4
       ],
       "multiple": [
        9,
        9
       ],
       "unsplittable": [
        10,
        10
       ],
       "number_rows": [
        12,
        12
       ],
       "answered_rows": [
        23,
        23
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "2",
        "unsplittable": "10",
        "number_rows": "12",
        "answered_rows": "23"
       }
      }
     },
     "gemma3:27b": {
      "plain": {
       "in_doc": [
        9,
        9
       ],
       "not_in_doc": [
        35,
        34
       ],
       "no_number": [
        2,
        2
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        5,
        5
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        8,
        8
       ],
       "unsplittable": [
        10,
        10
       ],
       "number_rows": [
        54,
        53
       ],
       "answered_rows": [
        83,
        81
       ],
       "disp": {
        "in_doc": "9",
        "not_in_doc": "34〜35",
        "unsplittable": "10",
        "number_rows": "53〜54",
        "answered_rows": "81〜83"
       }
      },
      "abstain": {
       "in_doc": [
        3,
        3
       ],
       "not_in_doc": [
        12,
        12
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        5,
        5
       ],
       "unsplittable": [
        6,
        6
       ],
       "number_rows": [
        21,
        21
       ],
       "answered_rows": [
        35,
        35
       ],
       "disp": {
        "in_doc": "3",
        "not_in_doc": "12",
        "unsplittable": "6",
        "number_rows": "21",
        "answered_rows": "35"
       }
      },
      "quote": {
       "in_doc": [
        5,
        4
       ],
       "not_in_doc": [
        12,
        12
       ],
       "no_number": [
        1,
        0
       ],
       "multiple_all_in_doc": [
        0,
        1
       ],
       "multiple_none_in_doc": [
        3,
        2
       ],
       "multiple_mixed": [
        7,
        7
       ],
       "multiple": [
        10,
        10
       ],
       "unsplittable": [
        11,
        10
       ],
       "number_rows": [
        28,
        26
       ],
       "answered_rows": [
        44,
        42
       ],
       "disp": {
        "in_doc": "4〜5",
        "not_in_doc": "12",
        "unsplittable": "10〜11",
        "number_rows": "26〜28",
        "answered_rows": "42〜44"
       }
      }
     },
     "gemma4:12b": {
      "plain": {
       "in_doc": [
        7,
        7
       ],
       "not_in_doc": [
        19,
        18
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        6,
        6
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        9,
        9
       ],
       "unsplittable": [
        10,
        10
       ],
       "number_rows": [
        36,
        35
       ],
       "answered_rows": [
        59,
        59
       ],
       "disp": {
        "in_doc": "7",
        "not_in_doc": "18〜19",
        "unsplittable": "10",
        "number_rows": "35〜36",
        "answered_rows": "59"
       }
      },
      "abstain": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        8,
        9
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        5,
        5
       ],
       "unsplittable": [
        5,
        5
       ],
       "number_rows": [
        14,
        15
       ],
       "answered_rows": [
        20,
        21
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "8〜9",
        "unsplittable": "5",
        "number_rows": "14〜15",
        "answered_rows": "20〜21"
       }
      },
      "quote": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        3,
        3
       ],
       "no_number": [
        3,
        3
       ],
       "multiple_all_in_doc": [
        2,
        2
       ],
       "multiple_none_in_doc": [
        3,
        3
       ],
       "multiple_mixed": [
        4,
        4
       ],
       "multiple": [
        9,
        9
       ],
       "unsplittable": [
        12,
        12
       ],
       "number_rows": [
        16,
        16
       ],
       "answered_rows": [
        25,
        24
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "3",
        "unsplittable": "12",
        "number_rows": "16",
        "answered_rows": "24〜25"
       }
      }
     },
     "gemma4:26b": {
      "plain": {
       "in_doc": [
        3,
        3
       ],
       "not_in_doc": [
        16,
        13
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        4,
        4
       ],
       "multiple_mixed": [
        3,
        3
       ],
       "multiple": [
        7,
        7
       ],
       "unsplittable": [
        8,
        8
       ],
       "number_rows": [
        27,
        24
       ],
       "answered_rows": [
        42,
        39
       ],
       "disp": {
        "in_doc": "3",
        "not_in_doc": "13〜16",
        "unsplittable": "8",
        "number_rows": "24〜27",
        "answered_rows": "39〜42"
       }
      },
      "abstain": {
       "in_doc": [
        2,
        2
       ],
       "not_in_doc": [
        7,
        8
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        4,
        4
       ],
       "unsplittable": [
        4,
        4
       ],
       "number_rows": [
        13,
        14
       ],
       "answered_rows": [
        19,
        20
       ],
       "disp": {
        "in_doc": "2",
        "not_in_doc": "7〜8",
        "unsplittable": "4",
        "number_rows": "13〜14",
        "answered_rows": "19〜20"
       }
      },
      "quote": {
       "in_doc": [
        3,
        3
       ],
       "not_in_doc": [
        4,
        4
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        1,
        1
       ],
       "multiple_mixed": [
        2,
        3
       ],
       "multiple": [
        3,
        4
       ],
       "unsplittable": [
        4,
        5
       ],
       "number_rows": [
        11,
        12
       ],
       "answered_rows": [
        16,
        17
       ],
       "disp": {
        "in_doc": "3",
        "not_in_doc": "4",
        "unsplittable": "4〜5",
        "number_rows": "11〜12",
        "answered_rows": "16〜17"
       }
      }
     },
     "gpt-oss:20b": {
      "plain": {
       "in_doc": [
        22,
        20
       ],
       "not_in_doc": [
        53,
        55
       ],
       "no_number": [
        2,
        2
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        10,
        10
       ],
       "multiple_mixed": [
        3,
        5
       ],
       "multiple": [
        13,
        15
       ],
       "unsplittable": [
        15,
        17
       ],
       "number_rows": [
        90,
        92
       ],
       "answered_rows": [
        134,
        138
       ],
       "disp": {
        "in_doc": "20〜22",
        "not_in_doc": "53〜55",
        "unsplittable": "15〜17",
        "number_rows": "90〜92",
        "answered_rows": "134〜138"
       }
      },
      "abstain": {
       "in_doc": [
        3,
        3
       ],
       "not_in_doc": [
        19,
        19
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        5,
        5
       ],
       "multiple_mixed": [
        1,
        1
       ],
       "multiple": [
        6,
        6
       ],
       "unsplittable": [
        6,
        6
       ],
       "number_rows": [
        28,
        28
       ],
       "answered_rows": [
        46,
        46
       ],
       "disp": {
        "in_doc": "3",
        "not_in_doc": "19",
        "unsplittable": "6",
        "number_rows": "28",
        "answered_rows": "46"
       }
      },
      "quote": {
       "in_doc": [
        3,
        3
       ],
       "not_in_doc": [
        11,
        14
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        4,
        3
       ],
       "multiple_mixed": [
        11,
        8
       ],
       "multiple": [
        15,
        11
       ],
       "unsplittable": [
        16,
        12
       ],
       "number_rows": [
        30,
        29
       ],
       "answered_rows": [
        46,
        45
       ],
       "disp": {
        "in_doc": "3",
        "not_in_doc": "11〜14",
        "unsplittable": "12〜16",
        "number_rows": "29〜30",
        "answered_rows": "45〜46"
       }
      }
     },
     "gpt-oss:120b": {
      "plain": {
       "in_doc": [
        20,
        21
       ],
       "not_in_doc": [
        57,
        54
       ],
       "no_number": [
        0,
        1
       ],
       "multiple_all_in_doc": [
        0,
        1
       ],
       "multiple_none_in_doc": [
        3,
        6
       ],
       "multiple_mixed": [
        3,
        2
       ],
       "multiple": [
        6,
        9
       ],
       "unsplittable": [
        6,
        10
       ],
       "number_rows": [
        83,
        85
       ],
       "answered_rows": [
        120,
        123
       ],
       "disp": {
        "in_doc": "20〜21",
        "not_in_doc": "54〜57",
        "unsplittable": "6〜10",
        "number_rows": "83〜85",
        "answered_rows": "120〜123"
       }
      },
      "abstain": {
       "in_doc": [
        1,
        0
       ],
       "not_in_doc": [
        8,
        7
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        1
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        0,
        1
       ],
       "multiple": [
        2,
        4
       ],
       "unsplittable": [
        2,
        4
       ],
       "number_rows": [
        11,
        11
       ],
       "answered_rows": [
        15,
        16
       ],
       "disp": {
        "in_doc": "0〜1",
        "not_in_doc": "7〜8",
        "unsplittable": "2〜4",
        "number_rows": "11",
        "answered_rows": "15〜16"
       }
      },
      "quote": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        2,
        1
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        1
       ],
       "multiple_none_in_doc": [
        3,
        2
       ],
       "multiple_mixed": [
        7,
        6
       ],
       "multiple": [
        10,
        9
       ],
       "unsplittable": [
        10,
        9
       ],
       "number_rows": [
        13,
        11
       ],
       "answered_rows": [
        21,
        17
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "1〜2",
        "unsplittable": "9〜10",
        "number_rows": "11〜13",
        "answered_rows": "17〜21"
       }
      }
     },
     "deepseek-r1:8b": {
      "plain": {
       "in_doc": [
        6,
        6
       ],
       "not_in_doc": [
        27,
        24
       ],
       "no_number": [
        0,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        8,
        7
       ],
       "multiple_mixed": [
        4,
        4
       ],
       "multiple": [
        12,
        11
       ],
       "unsplittable": [
        12,
        12
       ],
       "number_rows": [
        45,
        42
       ],
       "answered_rows": [
        71,
        69
       ],
       "disp": {
        "in_doc": "6",
        "not_in_doc": "24〜27",
        "unsplittable": "12",
        "number_rows": "42〜45",
        "answered_rows": "69〜71"
       }
      },
      "abstain": {
       "in_doc": [
        2,
        1
       ],
       "not_in_doc": [
        9,
        8
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        1,
        2
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        3,
        4
       ],
       "unsplittable": [
        3,
        4
       ],
       "number_rows": [
        14,
        13
       ],
       "answered_rows": [
        25,
        23
       ],
       "disp": {
        "in_doc": "1〜2",
        "not_in_doc": "8〜9",
        "unsplittable": "3〜4",
        "number_rows": "13〜14",
        "answered_rows": "23〜25"
       }
      },
      "quote": {
       "in_doc": [
        1,
        0
       ],
       "not_in_doc": [
        2,
        2
       ],
       "no_number": [
        0,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        1,
        3
       ],
       "multiple_mixed": [
        4,
        4
       ],
       "multiple": [
        5,
        7
       ],
       "unsplittable": [
        5,
        8
       ],
       "number_rows": [
        8,
        10
       ],
       "answered_rows": [
        19,
        18
       ],
       "disp": {
        "in_doc": "0〜1",
        "not_in_doc": "2",
        "unsplittable": "5〜8",
        "number_rows": "8〜10",
        "answered_rows": "18〜19"
       }
      }
     },
     "deepseek-r1:14b": {
      "plain": {
       "in_doc": [
        6,
        6
       ],
       "not_in_doc": [
        34,
        32
       ],
       "no_number": [
        2,
        3
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        6,
        6
       ],
       "multiple_mixed": [
        7,
        8
       ],
       "multiple": [
        13,
        14
       ],
       "unsplittable": [
        15,
        17
       ],
       "number_rows": [
        55,
        55
       ],
       "answered_rows": [
        92,
        90
       ],
       "disp": {
        "in_doc": "6",
        "not_in_doc": "32〜34",
        "unsplittable": "15〜17",
        "number_rows": "55",
        "answered_rows": "90〜92"
       }
      },
      "abstain": {
       "in_doc": [
        0,
        1
       ],
       "not_in_doc": [
        8,
        11
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        2,
        3
       ],
       "multiple_mixed": [
        4,
        1
       ],
       "multiple": [
        6,
        4
       ],
       "unsplittable": [
        6,
        4
       ],
       "number_rows": [
        14,
        16
       ],
       "answered_rows": [
        25,
        25
       ],
       "disp": {
        "in_doc": "0〜1",
        "not_in_doc": "8〜11",
        "unsplittable": "4〜6",
        "number_rows": "14〜16",
        "answered_rows": "25"
       }
      },
      "quote": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        4,
        6
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        3,
        6
       ],
       "multiple_mixed": [
        6,
        5
       ],
       "multiple": [
        10,
        12
       ],
       "unsplittable": [
        11,
        13
       ],
       "number_rows": [
        15,
        19
       ],
       "answered_rows": [
        29,
        32
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "4〜6",
        "unsplittable": "11〜13",
        "number_rows": "15〜19",
        "answered_rows": "29〜32"
       }
      }
     },
     "llama3.1:8b": {
      "plain": {
       "in_doc": [
        13,
        14
       ],
       "not_in_doc": [
        61,
        59
       ],
       "no_number": [
        4,
        4
       ],
       "multiple_all_in_doc": [
        1,
        2
       ],
       "multiple_none_in_doc": [
        13,
        14
       ],
       "multiple_mixed": [
        6,
        6
       ],
       "multiple": [
        20,
        22
       ],
       "unsplittable": [
        24,
        26
       ],
       "number_rows": [
        98,
        99
       ],
       "answered_rows": [
        135,
        135
       ],
       "disp": {
        "in_doc": "13〜14",
        "not_in_doc": "59〜61",
        "unsplittable": "24〜26",
        "number_rows": "98〜99",
        "answered_rows": "135"
       }
      },
      "abstain": {
       "in_doc": [
        1,
        0
       ],
       "not_in_doc": [
        10,
        11
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        6,
        6
       ],
       "multiple_mixed": [
        5,
        5
       ],
       "multiple": [
        11,
        11
       ],
       "unsplittable": [
        11,
        11
       ],
       "number_rows": [
        22,
        22
       ],
       "answered_rows": [
        28,
        27
       ],
       "disp": {
        "in_doc": "0〜1",
        "not_in_doc": "10〜11",
        "unsplittable": "11",
        "number_rows": "22",
        "answered_rows": "27〜28"
       }
      },
      "quote": {
       "in_doc": [
        6,
        5
       ],
       "not_in_doc": [
        25,
        27
       ],
       "no_number": [
        12,
        10
       ],
       "multiple_all_in_doc": [
        2,
        2
       ],
       "multiple_none_in_doc": [
        17,
        13
       ],
       "multiple_mixed": [
        21,
        21
       ],
       "multiple": [
        40,
        36
       ],
       "unsplittable": [
        52,
        46
       ],
       "number_rows": [
        83,
        78
       ],
       "answered_rows": [
        107,
        102
       ],
       "disp": {
        "in_doc": "5〜6",
        "not_in_doc": "25〜27",
        "unsplittable": "46〜52",
        "number_rows": "78〜83",
        "answered_rows": "102〜107"
       }
      }
     },
     "mistral-small3.2:24b": {
      "plain": {
       "in_doc": [
        10,
        11
       ],
       "not_in_doc": [
        37,
        39
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        11,
        11
       ],
       "multiple_mixed": [
        5,
        4
       ],
       "multiple": [
        16,
        15
       ],
       "unsplittable": [
        16,
        15
       ],
       "number_rows": [
        63,
        65
       ],
       "answered_rows": [
        100,
        102
       ],
       "disp": {
        "in_doc": "10〜11",
        "not_in_doc": "37〜39",
        "unsplittable": "15〜16",
        "number_rows": "63〜65",
        "answered_rows": "100〜102"
       }
      },
      "abstain": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        9,
        9
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        3,
        3
       ],
       "multiple": [
        5,
        5
       ],
       "unsplittable": [
        5,
        5
       ],
       "number_rows": [
        15,
        15
       ],
       "answered_rows": [
        28,
        28
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "9",
        "unsplittable": "5",
        "number_rows": "15",
        "answered_rows": "28"
       }
      },
      "quote": {
       "in_doc": [
        3,
        2
       ],
       "not_in_doc": [
        7,
        7
       ],
       "no_number": [
        1,
        2
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        8,
        8
       ],
       "multiple": [
        10,
        10
       ],
       "unsplittable": [
        11,
        12
       ],
       "number_rows": [
        21,
        21
       ],
       "answered_rows": [
        33,
        33
       ],
       "disp": {
        "in_doc": "2〜3",
        "not_in_doc": "7",
        "unsplittable": "11〜12",
        "number_rows": "21",
        "answered_rows": "33"
       }
      }
     },
     "phi4:14b": {
      "plain": {
       "in_doc": [
        2,
        2
       ],
       "not_in_doc": [
        5,
        3
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        3,
        3
       ],
       "multiple_none_in_doc": [
        14,
        12
       ],
       "multiple_mixed": [
        17,
        19
       ],
       "multiple": [
        34,
        34
       ],
       "unsplittable": [
        34,
        34
       ],
       "number_rows": [
        41,
        39
       ],
       "answered_rows": [
        68,
        66
       ],
       "disp": {
        "in_doc": "2",
        "not_in_doc": "3〜5",
        "unsplittable": "34",
        "number_rows": "39〜41",
        "answered_rows": "66〜68"
       }
      },
      "abstain": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        1,
        1
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        3,
        3
       ],
       "multiple_mixed": [
        6,
        6
       ],
       "multiple": [
        9,
        9
       ],
       "unsplittable": [
        9,
        9
       ],
       "number_rows": [
        10,
        10
       ],
       "answered_rows": [
        12,
        12
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "1",
        "unsplittable": "9",
        "number_rows": "10",
        "answered_rows": "12"
       }
      },
      "quote": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        1,
        1
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        2,
        1
       ],
       "multiple_mixed": [
        5,
        5
       ],
       "multiple": [
        7,
        6
       ],
       "unsplittable": [
        7,
        6
       ],
       "number_rows": [
        8,
        7
       ],
       "answered_rows": [
        12,
        11
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "1",
        "unsplittable": "6〜7",
        "number_rows": "7〜8",
        "answered_rows": "11〜12"
       }
      }
     }
    },
    "by_prompt": {
     "plain": {
      "in_doc": [
       153,
       151
      ],
      "not_in_doc": [
       566,
       548
      ],
      "no_number": [
       25,
       29
      ],
      "multiple_all_in_doc": [
       7,
       8
      ],
      "multiple_none_in_doc": [
       120,
       121
      ],
      "multiple_mixed": [
       73,
       77
      ],
      "multiple": [
       200,
       206
      ],
      "unsplittable": [
       225,
       235
      ],
      "number_rows": [
       944,
       934
      ],
      "answered_rows": [
       1442,
       1435
      ],
      "disp": {
       "in_doc": "151〜153",
       "not_in_doc": "548〜566",
       "unsplittable": "225〜235",
       "number_rows": "934〜944",
       "answered_rows": "1,435〜1,442"
      }
     },
     "abstain": {
      "in_doc": [
       24,
       22
      ],
      "not_in_doc": [
       142,
       150
      ],
      "no_number": [
       2,
       2
      ],
      "multiple_all_in_doc": [
       4,
       5
      ],
      "multiple_none_in_doc": [
       41,
       42
      ],
      "multiple_mixed": [
       34,
       33
      ],
      "multiple": [
       79,
       80
      ],
      "unsplittable": [
       81,
       82
      ],
      "number_rows": [
       247,
       254
      ],
      "answered_rows": [
       403,
       404
      ],
      "disp": {
       "in_doc": "22〜24",
       "not_in_doc": "142〜150",
       "unsplittable": "81〜82",
       "number_rows": "247〜254",
       "answered_rows": "403〜404"
      }
     },
     "quote": {
      "in_doc": [
       34,
       28
      ],
      "not_in_doc": [
       113,
       119
      ],
      "no_number": [
       22,
       23
      ],
      "multiple_all_in_doc": [
       8,
       10
      ],
      "multiple_none_in_doc": [
       53,
       49
      ],
      "multiple_mixed": [
       90,
       86
      ],
      "multiple": [
       151,
       145
      ],
      "unsplittable": [
       173,
       168
      ],
      "number_rows": [
       320,
       315
      ],
      "answered_rows": [
       495,
       483
      ],
      "disp": {
       "in_doc": "28〜34",
       "not_in_doc": "113〜119",
       "unsplittable": "168〜173",
       "number_rows": "315〜320",
       "answered_rows": "483〜495"
      }
     }
    }
   },
   "doc_numbers": {
    "questions": 118,
    "near_mean": "25.3",
    "far_mean": "19.6"
   }
  },
  "excluded": {
   "cells": {
    "qwen3:8b": {
     "plain": {
      "in_doc": [
       53,
       52
      ],
      "not_in_doc": [
       17,
       17
      ],
      "no_number": [
       1,
       2
      ],
      "multiple_all_in_doc": [
       10,
       10
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       5,
       4
      ],
      "multiple": [
       15,
       14
      ],
      "unsplittable": [
       16,
       16
      ],
      "number_rows": [
       86,
       85
      ],
      "answered_rows": [
       110,
       108
      ],
      "disp": {
       "in_doc": "52〜53",
       "not_in_doc": "17",
       "unsplittable": "16",
       "number_rows": "85〜86",
       "answered_rows": "108〜110"
      }
     },
     "abstain": {
      "in_doc": [
       7,
       7
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       3,
       3
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       2,
       2
      ],
      "multiple": [
       5,
       5
      ],
      "unsplittable": [
       5,
       5
      ],
      "number_rows": [
       12,
       12
      ],
      "answered_rows": [
       19,
       19
      ],
      "disp": {
       "in_doc": "7",
       "not_in_doc": "0",
       "unsplittable": "5",
       "number_rows": "12",
       "answered_rows": "19"
      }
     },
     "quote": {
      "in_doc": [
       9,
       9
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       1
      ],
      "multiple_all_in_doc": [
       2,
       2
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       2,
       2
      ],
      "multiple": [
       4,
       4
      ],
      "unsplittable": [
       4,
       5
      ],
      "number_rows": [
       13,
       14
      ],
      "answered_rows": [
       16,
       17
      ],
      "disp": {
       "in_doc": "9",
       "not_in_doc": "0",
       "unsplittable": "4〜5",
       "number_rows": "13〜14",
       "answered_rows": "16〜17"
      }
     }
    },
    "qwen3:14b": {
     "plain": {
      "in_doc": [
       42,
       43
      ],
      "not_in_doc": [
       11,
       12
      ],
      "no_number": [
       2,
       2
      ],
      "multiple_all_in_doc": [
       13,
       14
      ],
      "multiple_none_in_doc": [
       1,
       1
      ],
      "multiple_mixed": [
       2,
       2
      ],
      "multiple": [
       16,
       17
      ],
      "unsplittable": [
       18,
       19
      ],
      "number_rows": [
       71,
       74
      ],
      "answered_rows": [
       92,
       96
      ],
      "disp": {
       "in_doc": "42〜43",
       "not_in_doc": "11〜12",
       "unsplittable": "18〜19",
       "number_rows": "71〜74",
       "answered_rows": "92〜96"
      }
     },
     "abstain": {
      "in_doc": [
       6,
       6
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       6,
       6
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       6,
       6
      ],
      "unsplittable": [
       6,
       6
      ],
      "number_rows": [
       12,
       12
      ],
      "answered_rows": [
       18,
       18
      ],
      "disp": {
       "in_doc": "6",
       "not_in_doc": "0",
       "unsplittable": "6",
       "number_rows": "12",
       "answered_rows": "18"
      }
     },
     "quote": {
      "in_doc": [
       16,
       15
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       7,
       7
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       7,
       7
      ],
      "unsplittable": [
       8,
       8
      ],
      "number_rows": [
       24,
       23
      ],
      "answered_rows": [
       33,
       31
      ],
      "disp": {
       "in_doc": "15〜16",
       "not_in_doc": "0",
       "unsplittable": "8",
       "number_rows": "23〜24",
       "answered_rows": "31〜33"
      }
     }
    },
    "qwen3:30b": {
     "plain": {
      "in_doc": [
       38,
       28
      ],
      "not_in_doc": [
       13,
       14
      ],
      "no_number": [
       3,
       5
      ],
      "multiple_all_in_doc": [
       6,
       6
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       6,
       6
      ],
      "unsplittable": [
       9,
       11
      ],
      "number_rows": [
       60,
       53
      ],
      "answered_rows": [
       81,
       75
      ],
      "disp": {
       "in_doc": "28〜38",
       "not_in_doc": "13〜14",
       "unsplittable": "9〜11",
       "number_rows": "53〜60",
       "answered_rows": "75〜81"
      }
     },
     "abstain": {
      "in_doc": [
       11,
       16
      ],
      "not_in_doc": [
       3,
       1
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       3,
       3
      ],
      "multiple_none_in_doc": [
       1,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       4,
       3
      ],
      "unsplittable": [
       4,
       3
      ],
      "number_rows": [
       18,
       20
      ],
      "answered_rows": [
       22,
       23
      ],
      "disp": {
       "in_doc": "11〜16",
       "not_in_doc": "1〜3",
       "unsplittable": "3〜4",
       "number_rows": "18〜20",
       "answered_rows": "22〜23"
      }
     },
     "quote": {
      "in_doc": [
       9,
       10
      ],
      "not_in_doc": [
       2,
       1
      ],
      "no_number": [
       0,
       1
      ],
      "multiple_all_in_doc": [
       3,
       3
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       3,
       3
      ],
      "unsplittable": [
       3,
       4
      ],
      "number_rows": [
       14,
       15
      ],
      "answered_rows": [
       19,
       20
      ],
      "disp": {
       "in_doc": "9〜10",
       "not_in_doc": "1〜2",
       "unsplittable": "3〜4",
       "number_rows": "14〜15",
       "answered_rows": "19〜20"
      }
     }
    },
    "qwen3.5:9b": {
     "plain": {
      "in_doc": [
       26,
       26
      ],
      "not_in_doc": [
       3,
       4
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       8,
       8
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       8,
       8
      ],
      "unsplittable": [
       9,
       9
      ],
      "number_rows": [
       38,
       39
      ],
      "answered_rows": [
       48,
       49
      ],
      "disp": {
       "in_doc": "26",
       "not_in_doc": "3〜4",
       "unsplittable": "9",
       "number_rows": "38〜39",
       "answered_rows": "48〜49"
      }
     },
     "abstain": {
      "in_doc": [
       7,
       7
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       3,
       3
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       3,
       3
      ],
      "unsplittable": [
       3,
       3
      ],
      "number_rows": [
       10,
       10
      ],
      "answered_rows": [
       11,
       11
      ],
      "disp": {
       "in_doc": "7",
       "not_in_doc": "0",
       "unsplittable": "3",
       "number_rows": "10",
       "answered_rows": "11"
      }
     },
     "quote": {
      "in_doc": [
       1,
       1
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       2,
       2
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       2,
       2
      ],
      "unsplittable": [
       2,
       2
      ],
      "number_rows": [
       3,
       3
      ],
      "answered_rows": [
       5,
       5
      ],
      "disp": {
       "in_doc": "1",
       "not_in_doc": "0",
       "unsplittable": "2",
       "number_rows": "3",
       "answered_rows": "5"
      }
     }
    },
    "qwen3.5:27b": {
     "plain": {
      "in_doc": [
       9,
       8
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       5,
       6
      ],
      "multiple_none_in_doc": [
       1,
       1
      ],
      "multiple_mixed": [
       1,
       1
      ],
      "multiple": [
       7,
       8
      ],
      "unsplittable": [
       7,
       8
      ],
      "number_rows": [
       16,
       16
      ],
      "answered_rows": [
       23,
       23
      ],
      "disp": {
       "in_doc": "8〜9",
       "not_in_doc": "0",
       "unsplittable": "7〜8",
       "number_rows": "16",
       "answered_rows": "23"
      }
     },
     "abstain": {
      "in_doc": [
       0,
       0
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       0,
       0
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       0,
       0
      ],
      "unsplittable": [
       0,
       0
      ],
      "number_rows": [
       0,
       0
      ],
      "answered_rows": [
       1,
       1
      ],
      "disp": {
       "in_doc": "0",
       "not_in_doc": "0",
       "unsplittable": "0",
       "number_rows": "0",
       "answered_rows": "1"
      }
     },
     "quote": {
      "in_doc": [
       2,
       2
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       0,
       0
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       0,
       0
      ],
      "unsplittable": [
       0,
       0
      ],
      "number_rows": [
       2,
       2
      ],
      "answered_rows": [
       5,
       5
      ],
      "disp": {
       "in_doc": "2",
       "not_in_doc": "0",
       "unsplittable": "0",
       "number_rows": "2",
       "answered_rows": "5"
      }
     }
    },
    "gemma3:12b": {
     "plain": {
      "in_doc": [
       19,
       19
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       4,
       4
      ],
      "multiple_all_in_doc": [
       7,
       6
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       7,
       6
      ],
      "unsplittable": [
       11,
       10
      ],
      "number_rows": [
       30,
       29
      ],
      "answered_rows": [
       47,
       45
      ],
      "disp": {
       "in_doc": "19",
       "not_in_doc": "0",
       "unsplittable": "10〜11",
       "number_rows": "29〜30",
       "answered_rows": "45〜47"
      }
     },
     "abstain": {
      "in_doc": [
       4,
       4
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       3,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       3,
       4
      ],
      "unsplittable": [
       4,
       5
      ],
      "number_rows": [
       8,
       9
      ],
      "answered_rows": [
       17,
       18
      ],
      "disp": {
       "in_doc": "4",
       "not_in_doc": "0",
       "unsplittable": "4〜5",
       "number_rows": "8〜9",
       "answered_rows": "17〜18"
      }
     },
     "quote": {
      "in_doc": [
       2,
       2
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       5,
       5
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       5,
       5
      ],
      "unsplittable": [
       6,
       6
      ],
      "number_rows": [
       8,
       8
      ],
      "answered_rows": [
       13,
       13
      ],
      "disp": {
       "in_doc": "2",
       "not_in_doc": "0",
       "unsplittable": "6",
       "number_rows": "8",
       "answered_rows": "13"
      }
     }
    },
    "gemma3:27b": {
     "plain": {
      "in_doc": [
       33,
       33
      ],
      "not_in_doc": [
       4,
       3
      ],
      "no_number": [
       2,
       2
      ],
      "multiple_all_in_doc": [
       8,
       8
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       8,
       8
      ],
      "unsplittable": [
       10,
       10
      ],
      "number_rows": [
       47,
       46
      ],
      "answered_rows": [
       61,
       59
      ],
      "disp": {
       "in_doc": "33",
       "not_in_doc": "3〜4",
       "unsplittable": "10",
       "number_rows": "46〜47",
       "answered_rows": "59〜61"
      }
     },
     "abstain": {
      "in_doc": [
       11,
       10
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       5,
       5
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       5,
       5
      ],
      "unsplittable": [
       6,
       6
      ],
      "number_rows": [
       17,
       16
      ],
      "answered_rows": [
       24,
       23
      ],
      "disp": {
       "in_doc": "10〜11",
       "not_in_doc": "0",
       "unsplittable": "6",
       "number_rows": "16〜17",
       "answered_rows": "23〜24"
      }
     },
     "quote": {
      "in_doc": [
       13,
       12
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       6,
       7
      ],
      "multiple_none_in_doc": [
       1,
       0
      ],
      "multiple_mixed": [
       1,
       1
      ],
      "multiple": [
       8,
       8
      ],
      "unsplittable": [
       8,
       8
      ],
      "number_rows": [
       22,
       21
      ],
      "answered_rows": [
       30,
       29
      ],
      "disp": {
       "in_doc": "12〜13",
       "not_in_doc": "1",
       "unsplittable": "8",
       "number_rows": "21〜22",
       "answered_rows": "29〜30"
      }
     }
    },
    "gemma4:12b": {
     "plain": {
      "in_doc": [
       19,
       18
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       8,
       8
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       8,
       8
      ],
      "unsplittable": [
       8,
       8
      ],
      "number_rows": [
       27,
       26
      ],
      "answered_rows": [
       37,
       37
      ],
      "disp": {
       "in_doc": "18〜19",
       "not_in_doc": "0",
       "unsplittable": "8",
       "number_rows": "26〜27",
       "answered_rows": "37"
      }
     },
     "abstain": {
      "in_doc": [
       3,
       4
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       4,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       4,
       4
      ],
      "unsplittable": [
       4,
       4
      ],
      "number_rows": [
       7,
       8
      ],
      "answered_rows": [
       10,
       11
      ],
      "disp": {
       "in_doc": "3〜4",
       "not_in_doc": "0",
       "unsplittable": "4",
       "number_rows": "7〜8",
       "answered_rows": "10〜11"
      }
     },
     "quote": {
      "in_doc": [
       2,
       2
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       2,
       2
      ],
      "multiple_all_in_doc": [
       6,
       6
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       6,
       6
      ],
      "unsplittable": [
       8,
       8
      ],
      "number_rows": [
       10,
       10
      ],
      "answered_rows": [
       14,
       14
      ],
      "disp": {
       "in_doc": "2",
       "not_in_doc": "0",
       "unsplittable": "8",
       "number_rows": "10",
       "answered_rows": "14"
      }
     }
    },
    "gemma4:26b": {
     "plain": {
      "in_doc": [
       13,
       10
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       5,
       5
      ],
      "multiple_none_in_doc": [
       1,
       0
      ],
      "multiple_mixed": [
       1,
       2
      ],
      "multiple": [
       7,
       7
      ],
      "unsplittable": [
       8,
       8
      ],
      "number_rows": [
       21,
       18
      ],
      "answered_rows": [
       28,
       25
      ],
      "disp": {
       "in_doc": "10〜13",
       "not_in_doc": "0",
       "unsplittable": "8",
       "number_rows": "18〜21",
       "answered_rows": "25〜28"
      }
     },
     "abstain": {
      "in_doc": [
       3,
       4
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       4,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       4,
       4
      ],
      "unsplittable": [
       4,
       4
      ],
      "number_rows": [
       7,
       8
      ],
      "answered_rows": [
       10,
       11
      ],
      "disp": {
       "in_doc": "3〜4",
       "not_in_doc": "0",
       "unsplittable": "4",
       "number_rows": "7〜8",
       "answered_rows": "10〜11"
      }
     },
     "quote": {
      "in_doc": [
       3,
       3
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       3,
       3
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       3,
       3
      ],
      "unsplittable": [
       3,
       3
      ],
      "number_rows": [
       6,
       6
      ],
      "answered_rows": [
       9,
       9
      ],
      "disp": {
       "in_doc": "3",
       "not_in_doc": "0",
       "unsplittable": "3",
       "number_rows": "6",
       "answered_rows": "9"
      }
     }
    },
    "gpt-oss:20b": {
     "plain": {
      "in_doc": [
       38,
       38
      ],
      "not_in_doc": [
       27,
       27
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       7,
       11
      ],
      "multiple_none_in_doc": [
       3,
       1
      ],
      "multiple_mixed": [
       1,
       1
      ],
      "multiple": [
       11,
       13
      ],
      "unsplittable": [
       12,
       14
      ],
      "number_rows": [
       77,
       79
      ],
      "answered_rows": [
       102,
       105
      ],
      "disp": {
       "in_doc": "38",
       "not_in_doc": "27",
       "unsplittable": "12〜14",
       "number_rows": "77〜79",
       "answered_rows": "102〜105"
      }
     },
     "abstain": {
      "in_doc": [
       14,
       15
      ],
      "not_in_doc": [
       3,
       2
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       4,
       5
      ],
      "multiple_none_in_doc": [
       1,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       5,
       5
      ],
      "unsplittable": [
       5,
       5
      ],
      "number_rows": [
       22,
       22
      ],
      "answered_rows": [
       30,
       29
      ],
      "disp": {
       "in_doc": "14〜15",
       "not_in_doc": "2〜3",
       "unsplittable": "5",
       "number_rows": "22",
       "answered_rows": "29〜30"
      }
     },
     "quote": {
      "in_doc": [
       10,
       13
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       1,
       1
      ],
      "multiple_all_in_doc": [
       10,
       9
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       3,
       0
      ],
      "multiple": [
       13,
       9
      ],
      "unsplittable": [
       14,
       10
      ],
      "number_rows": [
       25,
       24
      ],
      "answered_rows": [
       33,
       32
      ],
      "disp": {
       "in_doc": "10〜13",
       "not_in_doc": "1",
       "unsplittable": "10〜14",
       "number_rows": "24〜25",
       "answered_rows": "32〜33"
      }
     }
    },
    "gpt-oss:120b": {
     "plain": {
      "in_doc": [
       40,
       34
      ],
      "not_in_doc": [
       28,
       29
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       3,
       6
      ],
      "multiple_none_in_doc": [
       1,
       2
      ],
      "multiple_mixed": [
       2,
       1
      ],
      "multiple": [
       6,
       9
      ],
      "unsplittable": [
       6,
       9
      ],
      "number_rows": [
       74,
       72
      ],
      "answered_rows": [
       95,
       94
      ],
      "disp": {
       "in_doc": "34〜40",
       "not_in_doc": "28〜29",
       "unsplittable": "6〜9",
       "number_rows": "72〜74",
       "answered_rows": "94〜95"
      }
     },
     "abstain": {
      "in_doc": [
       5,
       3
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       2,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       2,
       4
      ],
      "unsplittable": [
       2,
       4
      ],
      "number_rows": [
       7,
       7
      ],
      "answered_rows": [
       9,
       9
      ],
      "disp": {
       "in_doc": "3〜5",
       "not_in_doc": "0",
       "unsplittable": "2〜4",
       "number_rows": "7",
       "answered_rows": "9"
      }
     },
     "quote": {
      "in_doc": [
       3,
       2
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       5,
       6
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       2,
       1
      ],
      "multiple": [
       7,
       7
      ],
      "unsplittable": [
       7,
       7
      ],
      "number_rows": [
       10,
       9
      ],
      "answered_rows": [
       12,
       11
      ],
      "disp": {
       "in_doc": "2〜3",
       "not_in_doc": "0",
       "unsplittable": "7",
       "number_rows": "9〜10",
       "answered_rows": "11〜12"
      }
     }
    },
    "deepseek-r1:8b": {
     "plain": {
      "in_doc": [
       18,
       18
      ],
      "not_in_doc": [
       10,
       8
      ],
      "no_number": [
       0,
       1
      ],
      "multiple_all_in_doc": [
       7,
       4
      ],
      "multiple_none_in_doc": [
       2,
       1
      ],
      "multiple_mixed": [
       1,
       4
      ],
      "multiple": [
       10,
       9
      ],
      "unsplittable": [
       10,
       10
      ],
      "number_rows": [
       38,
       36
      ],
      "answered_rows": [
       49,
       48
      ],
      "disp": {
       "in_doc": "18",
       "not_in_doc": "8〜10",
       "unsplittable": "10",
       "number_rows": "36〜38",
       "answered_rows": "48〜49"
      }
     },
     "abstain": {
      "in_doc": [
       5,
       5
      ],
      "not_in_doc": [
       2,
       1
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       3,
       3
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       3,
       3
      ],
      "unsplittable": [
       3,
       3
      ],
      "number_rows": [
       10,
       9
      ],
      "answered_rows": [
       16,
       13
      ],
      "disp": {
       "in_doc": "5",
       "not_in_doc": "1〜2",
       "unsplittable": "3",
       "number_rows": "9〜10",
       "answered_rows": "13〜16"
      }
     },
     "quote": {
      "in_doc": [
       3,
       2
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       1
      ],
      "multiple_all_in_doc": [
       3,
       3
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       3,
       3
      ],
      "unsplittable": [
       3,
       4
      ],
      "number_rows": [
       6,
       6
      ],
      "answered_rows": [
       12,
       10
      ],
      "disp": {
       "in_doc": "2〜3",
       "not_in_doc": "0",
       "unsplittable": "3〜4",
       "number_rows": "6",
       "answered_rows": "10〜12"
      }
     }
    },
    "deepseek-r1:14b": {
     "plain": {
      "in_doc": [
       25,
       23
      ],
      "not_in_doc": [
       6,
       7
      ],
      "no_number": [
       2,
       2
      ],
      "multiple_all_in_doc": [
       7,
       10
      ],
      "multiple_none_in_doc": [
       1,
       0
      ],
      "multiple_mixed": [
       5,
       4
      ],
      "multiple": [
       13,
       14
      ],
      "unsplittable": [
       15,
       16
      ],
      "number_rows": [
       46,
       46
      ],
      "answered_rows": [
       65,
       64
      ],
      "disp": {
       "in_doc": "23〜25",
       "not_in_doc": "6〜7",
       "unsplittable": "15〜16",
       "number_rows": "46",
       "answered_rows": "64〜65"
      }
     },
     "abstain": {
      "in_doc": [
       3,
       5
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       4,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       2,
       0
      ],
      "multiple": [
       6,
       4
      ],
      "unsplittable": [
       6,
       4
      ],
      "number_rows": [
       9,
       9
      ],
      "answered_rows": [
       13,
       12
      ],
      "disp": {
       "in_doc": "3〜5",
       "not_in_doc": "0",
       "unsplittable": "4〜6",
       "number_rows": "9",
       "answered_rows": "12〜13"
      }
     },
     "quote": {
      "in_doc": [
       4,
       6
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       6,
       7
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       1
      ],
      "multiple": [
       6,
       8
      ],
      "unsplittable": [
       6,
       8
      ],
      "number_rows": [
       10,
       14
      ],
      "answered_rows": [
       15,
       19
      ],
      "disp": {
       "in_doc": "4〜6",
       "not_in_doc": "0",
       "unsplittable": "6〜8",
       "number_rows": "10〜14",
       "answered_rows": "15〜19"
      }
     }
    },
    "llama3.1:8b": {
     "plain": {
      "in_doc": [
       54,
       54
      ],
      "not_in_doc": [
       8,
       7
      ],
      "no_number": [
       4,
       4
      ],
      "multiple_all_in_doc": [
       14,
       15
      ],
      "multiple_none_in_doc": [
       1,
       1
      ],
      "multiple_mixed": [
       2,
       3
      ],
      "multiple": [
       17,
       19
      ],
      "unsplittable": [
       21,
       23
      ],
      "number_rows": [
       83,
       84
      ],
      "answered_rows": [
       102,
       103
      ],
      "disp": {
       "in_doc": "54",
       "not_in_doc": "7〜8",
       "unsplittable": "21〜23",
       "number_rows": "83〜84",
       "answered_rows": "102〜103"
      }
     },
     "abstain": {
      "in_doc": [
       7,
       7
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       9,
       9
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       9,
       9
      ],
      "unsplittable": [
       9,
       9
      ],
      "number_rows": [
       16,
       16
      ],
      "answered_rows": [
       19,
       19
      ],
      "disp": {
       "in_doc": "7",
       "not_in_doc": "0",
       "unsplittable": "9",
       "number_rows": "16",
       "answered_rows": "19"
      }
     },
     "quote": {
      "in_doc": [
       24,
       25
      ],
      "not_in_doc": [
       1,
       1
      ],
      "no_number": [
       10,
       9
      ],
      "multiple_all_in_doc": [
       32,
       27
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       5,
       6
      ],
      "multiple": [
       37,
       33
      ],
      "unsplittable": [
       47,
       42
      ],
      "number_rows": [
       72,
       68
      ],
      "answered_rows": [
       83,
       78
      ],
      "disp": {
       "in_doc": "24〜25",
       "not_in_doc": "1",
       "unsplittable": "42〜47",
       "number_rows": "68〜72",
       "answered_rows": "78〜83"
      }
     }
    },
    "mistral-small3.2:24b": {
     "plain": {
      "in_doc": [
       34,
       37
      ],
      "not_in_doc": [
       4,
       4
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       15,
       14
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       15,
       14
      ],
      "unsplittable": [
       15,
       14
      ],
      "number_rows": [
       53,
       55
      ],
      "answered_rows": [
       70,
       72
      ],
      "disp": {
       "in_doc": "34〜37",
       "not_in_doc": "4",
       "unsplittable": "14〜15",
       "number_rows": "53〜55",
       "answered_rows": "70〜72"
      }
     },
     "abstain": {
      "in_doc": [
       7,
       7
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       4,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       4,
       4
      ],
      "unsplittable": [
       4,
       4
      ],
      "number_rows": [
       11,
       11
      ],
      "answered_rows": [
       14,
       14
      ],
      "disp": {
       "in_doc": "7",
       "not_in_doc": "0",
       "unsplittable": "4",
       "number_rows": "11",
       "answered_rows": "14"
      }
     },
     "quote": {
      "in_doc": [
       7,
       6
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       1
      ],
      "multiple_all_in_doc": [
       5,
       5
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       2,
       2
      ],
      "multiple": [
       7,
       7
      ],
      "unsplittable": [
       7,
       8
      ],
      "number_rows": [
       14,
       14
      ],
      "answered_rows": [
       18,
       18
      ],
      "disp": {
       "in_doc": "6〜7",
       "not_in_doc": "0",
       "unsplittable": "7〜8",
       "number_rows": "14",
       "answered_rows": "18"
      }
     }
    },
    "phi4:14b": {
     "plain": {
      "in_doc": [
       4,
       2
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       18,
       18
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       11,
       11
      ],
      "multiple": [
       29,
       29
      ],
      "unsplittable": [
       29,
       29
      ],
      "number_rows": [
       33,
       31
      ],
      "answered_rows": [
       47,
       45
      ],
      "disp": {
       "in_doc": "2〜4",
       "not_in_doc": "0",
       "unsplittable": "29",
       "number_rows": "31〜33",
       "answered_rows": "45〜47"
      }
     },
     "abstain": {
      "in_doc": [
       1,
       1
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       4,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       1,
       1
      ],
      "multiple": [
       5,
       5
      ],
      "unsplittable": [
       5,
       5
      ],
      "number_rows": [
       6,
       6
      ],
      "answered_rows": [
       7,
       7
      ],
      "disp": {
       "in_doc": "1",
       "not_in_doc": "0",
       "unsplittable": "5",
       "number_rows": "6",
       "answered_rows": "7"
      }
     },
     "quote": {
      "in_doc": [
       1,
       1
      ],
      "not_in_doc": [
       0,
       0
      ],
      "no_number": [
       0,
       0
      ],
      "multiple_all_in_doc": [
       5,
       4
      ],
      "multiple_none_in_doc": [
       0,
       0
      ],
      "multiple_mixed": [
       0,
       0
      ],
      "multiple": [
       5,
       4
      ],
      "unsplittable": [
       5,
       4
      ],
      "number_rows": [
       6,
       5
      ],
      "answered_rows": [
       7,
       6
      ],
      "disp": {
       "in_doc": "1",
       "not_in_doc": "0",
       "unsplittable": "4〜5",
       "number_rows": "5〜6",
       "answered_rows": "6〜7"
      }
     }
    }
   },
   "by_prompt": {
    "plain": {
     "in_doc": [
      465,
      443
     ],
     "not_in_doc": [
      131,
      132
     ],
     "no_number": [
      21,
      25
     ],
     "multiple_all_in_doc": [
      141,
      149
     ],
     "multiple_none_in_doc": [
      11,
      7
     ],
     "multiple_mixed": [
      31,
      33
     ],
     "multiple": [
      183,
      189
     ],
     "unsplittable": [
      204,
      214
     ],
     "number_rows": [
      800,
      789
     ],
     "answered_rows": [
      1057,
      1048
     ],
     "disp": {
      "in_doc": "443〜465",
      "not_in_doc": "131〜132",
      "unsplittable": "204〜214",
      "number_rows": "789〜800",
      "answered_rows": "1,048〜1,057"
     }
    },
    "abstain": {
     "in_doc": [
      94,
      101
     ],
     "not_in_doc": [
      8,
      4
     ],
     "no_number": [
      2,
      2
     ],
     "multiple_all_in_doc": [
      61,
      65
     ],
     "multiple_none_in_doc": [
      2,
      0
     ],
     "multiple_mixed": [
      5,
      3
     ],
     "multiple": [
      68,
      68
     ],
     "unsplittable": [
      70,
      70
     ],
     "number_rows": [
      172,
      175
     ],
     "answered_rows": [
      240,
      238
     ],
     "disp": {
      "in_doc": "94〜101",
      "not_in_doc": "4〜8",
      "unsplittable": "70",
      "number_rows": "172〜175",
      "answered_rows": "238〜240"
     }
    },
    "quote": {
     "in_doc": [
      109,
      111
     ],
     "not_in_doc": [
      5,
      4
     ],
     "no_number": [
      15,
      18
     ],
     "multiple_all_in_doc": [
      100,
      96
     ],
     "multiple_none_in_doc": [
      1,
      0
     ],
     "multiple_mixed": [
      15,
      13
     ],
     "multiple": [
      116,
      109
     ],
     "unsplittable": [
      131,
      127
     ],
     "number_rows": [
      245,
      242
     ],
     "answered_rows": [
      324,
      317
     ],
     "disp": {
      "in_doc": "109〜111",
      "not_in_doc": "4〜5",
      "unsplittable": "127〜131",
      "number_rows": "242〜245",
      "answered_rows": "317〜324"
     }
    }
   },
   "control_far": {
    "cells": {
     "qwen3:8b": {
      "plain": {
       "in_doc": [
        11,
        12
       ],
       "not_in_doc": [
        59,
        57
       ],
       "no_number": [
        1,
        2
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        11,
        11
       ],
       "multiple_mixed": [
        4,
        3
       ],
       "multiple": [
        15,
        14
       ],
       "unsplittable": [
        16,
        16
       ],
       "number_rows": [
        86,
        85
       ],
       "answered_rows": [
        110,
        108
       ],
       "disp": {
        "in_doc": "11〜12",
        "not_in_doc": "57〜59",
        "unsplittable": "16",
        "number_rows": "85〜86",
        "answered_rows": "108〜110"
       }
      },
      "abstain": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        7,
        7
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        3,
        3
       ],
       "multiple_mixed": [
        1,
        1
       ],
       "multiple": [
        5,
        5
       ],
       "unsplittable": [
        5,
        5
       ],
       "number_rows": [
        12,
        12
       ],
       "answered_rows": [
        19,
        19
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "7",
        "unsplittable": "5",
        "number_rows": "12",
        "answered_rows": "19"
       }
      },
      "quote": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        8,
        8
       ],
       "no_number": [
        0,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        4,
        4
       ],
       "unsplittable": [
        4,
        5
       ],
       "number_rows": [
        13,
        14
       ],
       "answered_rows": [
        16,
        17
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "8",
        "unsplittable": "4〜5",
        "number_rows": "13〜14",
        "answered_rows": "16〜17"
       }
      }
     },
     "qwen3:14b": {
      "plain": {
       "in_doc": [
        10,
        10
       ],
       "not_in_doc": [
        43,
        45
       ],
       "no_number": [
        2,
        2
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        11,
        12
       ],
       "multiple_mixed": [
        5,
        5
       ],
       "multiple": [
        16,
        17
       ],
       "unsplittable": [
        18,
        19
       ],
       "number_rows": [
        71,
        74
       ],
       "answered_rows": [
        92,
        96
       ],
       "disp": {
        "in_doc": "10",
        "not_in_doc": "43〜45",
        "unsplittable": "18〜19",
        "number_rows": "71〜74",
        "answered_rows": "92〜96"
       }
      },
      "abstain": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        6,
        6
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        4,
        4
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        6,
        6
       ],
       "unsplittable": [
        6,
        6
       ],
       "number_rows": [
        12,
        12
       ],
       "answered_rows": [
        18,
        18
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "6",
        "unsplittable": "6",
        "number_rows": "12",
        "answered_rows": "18"
       }
      },
      "quote": {
       "in_doc": [
        4,
        3
       ],
       "not_in_doc": [
        12,
        12
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        3,
        3
       ],
       "multiple_mixed": [
        4,
        4
       ],
       "multiple": [
        7,
        7
       ],
       "unsplittable": [
        8,
        8
       ],
       "number_rows": [
        24,
        23
       ],
       "answered_rows": [
        33,
        31
       ],
       "disp": {
        "in_doc": "3〜4",
        "not_in_doc": "12",
        "unsplittable": "8",
        "number_rows": "23〜24",
        "answered_rows": "31〜33"
       }
      }
     },
     "qwen3:30b": {
      "plain": {
       "in_doc": [
        11,
        10
       ],
       "not_in_doc": [
        40,
        32
       ],
       "no_number": [
        3,
        5
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        5,
        4
       ],
       "multiple_mixed": [
        1,
        2
       ],
       "multiple": [
        6,
        6
       ],
       "unsplittable": [
        9,
        11
       ],
       "number_rows": [
        60,
        53
       ],
       "answered_rows": [
        81,
        75
       ],
       "disp": {
        "in_doc": "10〜11",
        "not_in_doc": "32〜40",
        "unsplittable": "9〜11",
        "number_rows": "53〜60",
        "answered_rows": "75〜81"
       }
      },
      "abstain": {
       "in_doc": [
        4,
        4
       ],
       "not_in_doc": [
        10,
        13
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        3,
        2
       ],
       "multiple_mixed": [
        1,
        1
       ],
       "multiple": [
        4,
        3
       ],
       "unsplittable": [
        4,
        3
       ],
       "number_rows": [
        18,
        20
       ],
       "answered_rows": [
        22,
        23
       ],
       "disp": {
        "in_doc": "4",
        "not_in_doc": "10〜13",
        "unsplittable": "3〜4",
        "number_rows": "18〜20",
        "answered_rows": "22〜23"
       }
      },
      "quote": {
       "in_doc": [
        3,
        3
       ],
       "not_in_doc": [
        8,
        8
       ],
       "no_number": [
        0,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        1,
        1
       ],
       "multiple": [
        3,
        3
       ],
       "unsplittable": [
        3,
        4
       ],
       "number_rows": [
        14,
        15
       ],
       "answered_rows": [
        19,
        20
       ],
       "disp": {
        "in_doc": "3",
        "not_in_doc": "8",
        "unsplittable": "3〜4",
        "number_rows": "14〜15",
        "answered_rows": "19〜20"
       }
      }
     },
     "qwen3.5:9b": {
      "plain": {
       "in_doc": [
        4,
        4
       ],
       "not_in_doc": [
        25,
        26
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        4,
        4
       ],
       "multiple_mixed": [
        4,
        4
       ],
       "multiple": [
        8,
        8
       ],
       "unsplittable": [
        9,
        9
       ],
       "number_rows": [
        38,
        39
       ],
       "answered_rows": [
        48,
        49
       ],
       "disp": {
        "in_doc": "4",
        "not_in_doc": "25〜26",
        "unsplittable": "9",
        "number_rows": "38〜39",
        "answered_rows": "48〜49"
       }
      },
      "abstain": {
       "in_doc": [
        2,
        2
       ],
       "not_in_doc": [
        5,
        5
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        1,
        1
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        3,
        3
       ],
       "unsplittable": [
        3,
        3
       ],
       "number_rows": [
        10,
        10
       ],
       "answered_rows": [
        11,
        11
       ],
       "disp": {
        "in_doc": "2",
        "not_in_doc": "5",
        "unsplittable": "3",
        "number_rows": "10",
        "answered_rows": "11"
       }
      },
      "quote": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        1,
        1
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        1,
        1
       ],
       "multiple_mixed": [
        1,
        1
       ],
       "multiple": [
        2,
        2
       ],
       "unsplittable": [
        2,
        2
       ],
       "number_rows": [
        3,
        3
       ],
       "answered_rows": [
        5,
        5
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "1",
        "unsplittable": "2",
        "number_rows": "3",
        "answered_rows": "5"
       }
      }
     },
     "qwen3.5:27b": {
      "plain": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        8,
        7
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        4,
        4
       ],
       "multiple_mixed": [
        3,
        4
       ],
       "multiple": [
        7,
        8
       ],
       "unsplittable": [
        7,
        8
       ],
       "number_rows": [
        16,
        16
       ],
       "answered_rows": [
        23,
        23
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "7〜8",
        "unsplittable": "7〜8",
        "number_rows": "16",
        "answered_rows": "23"
       }
      },
      "abstain": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        0,
        0
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        0,
        0
       ],
       "multiple_mixed": [
        0,
        0
       ],
       "multiple": [
        0,
        0
       ],
       "unsplittable": [
        0,
        0
       ],
       "number_rows": [
        0,
        0
       ],
       "answered_rows": [
        1,
        1
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "0",
        "unsplittable": "0",
        "number_rows": "0",
        "answered_rows": "1"
       }
      },
      "quote": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        1,
        1
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        0,
        0
       ],
       "multiple_mixed": [
        0,
        0
       ],
       "multiple": [
        0,
        0
       ],
       "unsplittable": [
        0,
        0
       ],
       "number_rows": [
        2,
        2
       ],
       "answered_rows": [
        5,
        5
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "1",
        "unsplittable": "0",
        "number_rows": "2",
        "answered_rows": "5"
       }
      }
     },
     "gemma3:12b": {
      "plain": {
       "in_doc": [
        3,
        2
       ],
       "not_in_doc": [
        16,
        17
       ],
       "no_number": [
        4,
        4
       ],
       "multiple_all_in_doc": [
        1,
        0
       ],
       "multiple_none_in_doc": [
        3,
        3
       ],
       "multiple_mixed": [
        3,
        3
       ],
       "multiple": [
        7,
        6
       ],
       "unsplittable": [
        11,
        10
       ],
       "number_rows": [
        30,
        29
       ],
       "answered_rows": [
        47,
        45
       ],
       "disp": {
        "in_doc": "2〜3",
        "not_in_doc": "16〜17",
        "unsplittable": "10〜11",
        "number_rows": "29〜30",
        "answered_rows": "45〜47"
       }
      },
      "abstain": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        4,
        4
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        1,
        1
       ],
       "multiple_mixed": [
        1,
        2
       ],
       "multiple": [
        3,
        4
       ],
       "unsplittable": [
        4,
        5
       ],
       "number_rows": [
        8,
        9
       ],
       "answered_rows": [
        17,
        18
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "4",
        "unsplittable": "4〜5",
        "number_rows": "8〜9",
        "answered_rows": "17〜18"
       }
      },
      "quote": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        2,
        2
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        1,
        1
       ],
       "multiple_mixed": [
        3,
        3
       ],
       "multiple": [
        5,
        5
       ],
       "unsplittable": [
        6,
        6
       ],
       "number_rows": [
        8,
        8
       ],
       "answered_rows": [
        13,
        13
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "2",
        "unsplittable": "6",
        "number_rows": "8",
        "answered_rows": "13"
       }
      }
     },
     "gemma3:27b": {
      "plain": {
       "in_doc": [
        6,
        6
       ],
       "not_in_doc": [
        31,
        30
       ],
       "no_number": [
        2,
        2
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        5,
        5
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        8,
        8
       ],
       "unsplittable": [
        10,
        10
       ],
       "number_rows": [
        47,
        46
       ],
       "answered_rows": [
        61,
        59
       ],
       "disp": {
        "in_doc": "6",
        "not_in_doc": "30〜31",
        "unsplittable": "10",
        "number_rows": "46〜47",
        "answered_rows": "59〜61"
       }
      },
      "abstain": {
       "in_doc": [
        2,
        2
       ],
       "not_in_doc": [
        9,
        8
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        5,
        5
       ],
       "unsplittable": [
        6,
        6
       ],
       "number_rows": [
        17,
        16
       ],
       "answered_rows": [
        24,
        23
       ],
       "disp": {
        "in_doc": "2",
        "not_in_doc": "8〜9",
        "unsplittable": "6",
        "number_rows": "16〜17",
        "answered_rows": "23〜24"
       }
      },
      "quote": {
       "in_doc": [
        4,
        3
       ],
       "not_in_doc": [
        10,
        10
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        1
       ],
       "multiple_none_in_doc": [
        3,
        2
       ],
       "multiple_mixed": [
        5,
        5
       ],
       "multiple": [
        8,
        8
       ],
       "unsplittable": [
        8,
        8
       ],
       "number_rows": [
        22,
        21
       ],
       "answered_rows": [
        30,
        29
       ],
       "disp": {
        "in_doc": "3〜4",
        "not_in_doc": "10",
        "unsplittable": "8",
        "number_rows": "21〜22",
        "answered_rows": "29〜30"
       }
      }
     },
     "gemma4:12b": {
      "plain": {
       "in_doc": [
        4,
        4
       ],
       "not_in_doc": [
        15,
        14
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        5,
        5
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        8,
        8
       ],
       "unsplittable": [
        8,
        8
       ],
       "number_rows": [
        27,
        26
       ],
       "answered_rows": [
        37,
        37
       ],
       "disp": {
        "in_doc": "4",
        "not_in_doc": "14〜15",
        "unsplittable": "8",
        "number_rows": "26〜27",
        "answered_rows": "37"
       }
      },
      "abstain": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        3,
        4
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        1,
        1
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        4,
        4
       ],
       "unsplittable": [
        4,
        4
       ],
       "number_rows": [
        7,
        8
       ],
       "answered_rows": [
        10,
        11
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "3〜4",
        "unsplittable": "4",
        "number_rows": "7〜8",
        "answered_rows": "10〜11"
       }
      },
      "quote": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        2,
        2
       ],
       "no_number": [
        2,
        2
       ],
       "multiple_all_in_doc": [
        2,
        2
       ],
       "multiple_none_in_doc": [
        1,
        1
       ],
       "multiple_mixed": [
        3,
        3
       ],
       "multiple": [
        6,
        6
       ],
       "unsplittable": [
        8,
        8
       ],
       "number_rows": [
        10,
        10
       ],
       "answered_rows": [
        14,
        14
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "2",
        "unsplittable": "8",
        "number_rows": "10",
        "answered_rows": "14"
       }
      }
     },
     "gemma4:26b": {
      "plain": {
       "in_doc": [
        2,
        2
       ],
       "not_in_doc": [
        11,
        8
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        4,
        4
       ],
       "multiple_mixed": [
        3,
        3
       ],
       "multiple": [
        7,
        7
       ],
       "unsplittable": [
        8,
        8
       ],
       "number_rows": [
        21,
        18
       ],
       "answered_rows": [
        28,
        25
       ],
       "disp": {
        "in_doc": "2",
        "not_in_doc": "8〜11",
        "unsplittable": "8",
        "number_rows": "18〜21",
        "answered_rows": "25〜28"
       }
      },
      "abstain": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        2,
        3
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        4,
        4
       ],
       "unsplittable": [
        4,
        4
       ],
       "number_rows": [
        7,
        8
       ],
       "answered_rows": [
        10,
        11
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "2〜3",
        "unsplittable": "4",
        "number_rows": "7〜8",
        "answered_rows": "10〜11"
       }
      },
      "quote": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        2,
        2
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        1,
        1
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        3,
        3
       ],
       "unsplittable": [
        3,
        3
       ],
       "number_rows": [
        6,
        6
       ],
       "answered_rows": [
        9,
        9
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "2",
        "unsplittable": "3",
        "number_rows": "6",
        "answered_rows": "9"
       }
      }
     },
     "gpt-oss:20b": {
      "plain": {
       "in_doc": [
        18,
        16
       ],
       "not_in_doc": [
        47,
        49
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        8,
        8
       ],
       "multiple_mixed": [
        3,
        5
       ],
       "multiple": [
        11,
        13
       ],
       "unsplittable": [
        12,
        14
       ],
       "number_rows": [
        77,
        79
       ],
       "answered_rows": [
        102,
        105
       ],
       "disp": {
        "in_doc": "16〜18",
        "not_in_doc": "47〜49",
        "unsplittable": "12〜14",
        "number_rows": "77〜79",
        "answered_rows": "102〜105"
       }
      },
      "abstain": {
       "in_doc": [
        2,
        2
       ],
       "not_in_doc": [
        15,
        15
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        4,
        4
       ],
       "multiple_mixed": [
        1,
        1
       ],
       "multiple": [
        5,
        5
       ],
       "unsplittable": [
        5,
        5
       ],
       "number_rows": [
        22,
        22
       ],
       "answered_rows": [
        30,
        29
       ],
       "disp": {
        "in_doc": "2",
        "not_in_doc": "15",
        "unsplittable": "5",
        "number_rows": "22",
        "answered_rows": "29〜30"
       }
      },
      "quote": {
       "in_doc": [
        2,
        2
       ],
       "not_in_doc": [
        9,
        12
       ],
       "no_number": [
        1,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        3,
        3
       ],
       "multiple_mixed": [
        10,
        6
       ],
       "multiple": [
        13,
        9
       ],
       "unsplittable": [
        14,
        10
       ],
       "number_rows": [
        25,
        24
       ],
       "answered_rows": [
        33,
        32
       ],
       "disp": {
        "in_doc": "2",
        "not_in_doc": "9〜12",
        "unsplittable": "10〜14",
        "number_rows": "24〜25",
        "answered_rows": "32〜33"
       }
      }
     },
     "gpt-oss:120b": {
      "plain": {
       "in_doc": [
        16,
        16
       ],
       "not_in_doc": [
        52,
        47
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        1
       ],
       "multiple_none_in_doc": [
        3,
        6
       ],
       "multiple_mixed": [
        3,
        2
       ],
       "multiple": [
        6,
        9
       ],
       "unsplittable": [
        6,
        9
       ],
       "number_rows": [
        74,
        72
       ],
       "answered_rows": [
        95,
        94
       ],
       "disp": {
        "in_doc": "16",
        "not_in_doc": "47〜52",
        "unsplittable": "6〜9",
        "number_rows": "72〜74",
        "answered_rows": "94〜95"
       }
      },
      "abstain": {
       "in_doc": [
        1,
        0
       ],
       "not_in_doc": [
        4,
        3
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        1
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        0,
        1
       ],
       "multiple": [
        2,
        4
       ],
       "unsplittable": [
        2,
        4
       ],
       "number_rows": [
        7,
        7
       ],
       "answered_rows": [
        9,
        9
       ],
       "disp": {
        "in_doc": "0〜1",
        "not_in_doc": "3〜4",
        "unsplittable": "2〜4",
        "number_rows": "7",
        "answered_rows": "9"
       }
      },
      "quote": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        2,
        1
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        1
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        5,
        4
       ],
       "multiple": [
        7,
        7
       ],
       "unsplittable": [
        7,
        7
       ],
       "number_rows": [
        10,
        9
       ],
       "answered_rows": [
        12,
        11
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "1〜2",
        "unsplittable": "7",
        "number_rows": "9〜10",
        "answered_rows": "11〜12"
       }
      }
     },
     "deepseek-r1:8b": {
      "plain": {
       "in_doc": [
        4,
        4
       ],
       "not_in_doc": [
        24,
        22
       ],
       "no_number": [
        0,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        7,
        6
       ],
       "multiple_mixed": [
        3,
        3
       ],
       "multiple": [
        10,
        9
       ],
       "unsplittable": [
        10,
        10
       ],
       "number_rows": [
        38,
        36
       ],
       "answered_rows": [
        49,
        48
       ],
       "disp": {
        "in_doc": "4",
        "not_in_doc": "22〜24",
        "unsplittable": "10",
        "number_rows": "36〜38",
        "answered_rows": "48〜49"
       }
      },
      "abstain": {
       "in_doc": [
        1,
        0
       ],
       "not_in_doc": [
        6,
        6
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        1,
        1
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        3,
        3
       ],
       "unsplittable": [
        3,
        3
       ],
       "number_rows": [
        10,
        9
       ],
       "answered_rows": [
        16,
        13
       ],
       "disp": {
        "in_doc": "0〜1",
        "not_in_doc": "6",
        "unsplittable": "3",
        "number_rows": "9〜10",
        "answered_rows": "13〜16"
       }
      },
      "quote": {
       "in_doc": [
        1,
        0
       ],
       "not_in_doc": [
        2,
        2
       ],
       "no_number": [
        0,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        0,
        1
       ],
       "multiple_mixed": [
        3,
        2
       ],
       "multiple": [
        3,
        3
       ],
       "unsplittable": [
        3,
        4
       ],
       "number_rows": [
        6,
        6
       ],
       "answered_rows": [
        12,
        10
       ],
       "disp": {
        "in_doc": "0〜1",
        "not_in_doc": "2",
        "unsplittable": "3〜4",
        "number_rows": "6",
        "answered_rows": "10〜12"
       }
      }
     },
     "deepseek-r1:14b": {
      "plain": {
       "in_doc": [
        4,
        4
       ],
       "not_in_doc": [
        27,
        26
       ],
       "no_number": [
        2,
        2
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        6,
        6
       ],
       "multiple_mixed": [
        7,
        8
       ],
       "multiple": [
        13,
        14
       ],
       "unsplittable": [
        15,
        16
       ],
       "number_rows": [
        46,
        46
       ],
       "answered_rows": [
        65,
        64
       ],
       "disp": {
        "in_doc": "4",
        "not_in_doc": "26〜27",
        "unsplittable": "15〜16",
        "number_rows": "46",
        "answered_rows": "64〜65"
       }
      },
      "abstain": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        3,
        5
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        2,
        3
       ],
       "multiple_mixed": [
        4,
        1
       ],
       "multiple": [
        6,
        4
       ],
       "unsplittable": [
        6,
        4
       ],
       "number_rows": [
        9,
        9
       ],
       "answered_rows": [
        13,
        12
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "3〜5",
        "unsplittable": "4〜6",
        "number_rows": "9",
        "answered_rows": "12〜13"
       }
      },
      "quote": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        4,
        6
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        2,
        5
       ],
       "multiple_mixed": [
        4,
        3
       ],
       "multiple": [
        6,
        8
       ],
       "unsplittable": [
        6,
        8
       ],
       "number_rows": [
        10,
        14
       ],
       "answered_rows": [
        15,
        19
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "4〜6",
        "unsplittable": "6〜8",
        "number_rows": "10〜14",
        "answered_rows": "15〜19"
       }
      }
     },
     "llama3.1:8b": {
      "plain": {
       "in_doc": [
        8,
        10
       ],
       "not_in_doc": [
        54,
        51
       ],
       "no_number": [
        4,
        4
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        12,
        13
       ],
       "multiple_mixed": [
        4,
        5
       ],
       "multiple": [
        17,
        19
       ],
       "unsplittable": [
        21,
        23
       ],
       "number_rows": [
        83,
        84
       ],
       "answered_rows": [
        102,
        103
       ],
       "disp": {
        "in_doc": "8〜10",
        "not_in_doc": "51〜54",
        "unsplittable": "21〜23",
        "number_rows": "83〜84",
        "answered_rows": "102〜103"
       }
      },
      "abstain": {
       "in_doc": [
        1,
        0
       ],
       "not_in_doc": [
        6,
        7
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        5,
        5
       ],
       "multiple_mixed": [
        4,
        4
       ],
       "multiple": [
        9,
        9
       ],
       "unsplittable": [
        9,
        9
       ],
       "number_rows": [
        16,
        16
       ],
       "answered_rows": [
        19,
        19
       ],
       "disp": {
        "in_doc": "0〜1",
        "not_in_doc": "6〜7",
        "unsplittable": "9",
        "number_rows": "16",
        "answered_rows": "19"
       }
      },
      "quote": {
       "in_doc": [
        4,
        3
       ],
       "not_in_doc": [
        21,
        23
       ],
       "no_number": [
        10,
        9
       ],
       "multiple_all_in_doc": [
        2,
        2
       ],
       "multiple_none_in_doc": [
        16,
        12
       ],
       "multiple_mixed": [
        19,
        19
       ],
       "multiple": [
        37,
        33
       ],
       "unsplittable": [
        47,
        42
       ],
       "number_rows": [
        72,
        68
       ],
       "answered_rows": [
        83,
        78
       ],
       "disp": {
        "in_doc": "3〜4",
        "not_in_doc": "21〜23",
        "unsplittable": "42〜47",
        "number_rows": "68〜72",
        "answered_rows": "78〜83"
       }
      }
     },
     "mistral-small3.2:24b": {
      "plain": {
       "in_doc": [
        7,
        8
       ],
       "not_in_doc": [
        31,
        33
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        10,
        10
       ],
       "multiple_mixed": [
        5,
        4
       ],
       "multiple": [
        15,
        14
       ],
       "unsplittable": [
        15,
        14
       ],
       "number_rows": [
        53,
        55
       ],
       "answered_rows": [
        70,
        72
       ],
       "disp": {
        "in_doc": "7〜8",
        "not_in_doc": "31〜33",
        "unsplittable": "14〜15",
        "number_rows": "53〜55",
        "answered_rows": "70〜72"
       }
      },
      "abstain": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        6,
        6
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        2,
        2
       ],
       "multiple_mixed": [
        2,
        2
       ],
       "multiple": [
        4,
        4
       ],
       "unsplittable": [
        4,
        4
       ],
       "number_rows": [
        11,
        11
       ],
       "answered_rows": [
        14,
        14
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "6",
        "unsplittable": "4",
        "number_rows": "11",
        "answered_rows": "14"
       }
      },
      "quote": {
       "in_doc": [
        2,
        1
       ],
       "not_in_doc": [
        5,
        5
       ],
       "no_number": [
        0,
        1
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        1,
        1
       ],
       "multiple_mixed": [
        6,
        6
       ],
       "multiple": [
        7,
        7
       ],
       "unsplittable": [
        7,
        8
       ],
       "number_rows": [
        14,
        14
       ],
       "answered_rows": [
        18,
        18
       ],
       "disp": {
        "in_doc": "1〜2",
        "not_in_doc": "5",
        "unsplittable": "7〜8",
        "number_rows": "14",
        "answered_rows": "18"
       }
      }
     },
     "phi4:14b": {
      "plain": {
       "in_doc": [
        1,
        1
       ],
       "not_in_doc": [
        3,
        1
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        1,
        1
       ],
       "multiple_none_in_doc": [
        13,
        11
       ],
       "multiple_mixed": [
        15,
        17
       ],
       "multiple": [
        29,
        29
       ],
       "unsplittable": [
        29,
        29
       ],
       "number_rows": [
        33,
        31
       ],
       "answered_rows": [
        47,
        45
       ],
       "disp": {
        "in_doc": "1",
        "not_in_doc": "1〜3",
        "unsplittable": "29",
        "number_rows": "31〜33",
        "answered_rows": "45〜47"
       }
      },
      "abstain": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        1,
        1
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        1,
        1
       ],
       "multiple_mixed": [
        4,
        4
       ],
       "multiple": [
        5,
        5
       ],
       "unsplittable": [
        5,
        5
       ],
       "number_rows": [
        6,
        6
       ],
       "answered_rows": [
        7,
        7
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "1",
        "unsplittable": "5",
        "number_rows": "6",
        "answered_rows": "7"
       }
      },
      "quote": {
       "in_doc": [
        0,
        0
       ],
       "not_in_doc": [
        1,
        1
       ],
       "no_number": [
        0,
        0
       ],
       "multiple_all_in_doc": [
        0,
        0
       ],
       "multiple_none_in_doc": [
        2,
        1
       ],
       "multiple_mixed": [
        3,
        3
       ],
       "multiple": [
        5,
        4
       ],
       "unsplittable": [
        5,
        4
       ],
       "number_rows": [
        6,
        5
       ],
       "answered_rows": [
        7,
        6
       ],
       "disp": {
        "in_doc": "0",
        "not_in_doc": "1",
        "unsplittable": "4〜5",
        "number_rows": "5〜6",
        "answered_rows": "6〜7"
       }
      }
     }
    },
    "by_prompt": {
     "plain": {
      "in_doc": [
       110,
       110
      ],
      "not_in_doc": [
       486,
       465
      ],
      "no_number": [
       21,
       25
      ],
      "multiple_all_in_doc": [
       5,
       5
      ],
      "multiple_none_in_doc": [
       111,
       112
      ],
      "multiple_mixed": [
       67,
       72
      ],
      "multiple": [
       183,
       189
      ],
      "unsplittable": [
       204,
       214
      ],
      "number_rows": [
       800,
       789
      ],
      "answered_rows": [
       1057,
       1048
      ],
      "disp": {
       "in_doc": "110",
       "not_in_doc": "465〜486",
       "unsplittable": "204〜214",
       "number_rows": "789〜800",
       "answered_rows": "1,048〜1,057"
      }
     },
     "abstain": {
      "in_doc": [
       15,
       12
      ],
      "not_in_doc": [
       87,
       93
      ],
      "no_number": [
       2,
       2
      ],
      "multiple_all_in_doc": [
       4,
       5
      ],
      "multiple_none_in_doc": [
       34,
       34
      ],
      "multiple_mixed": [
       30,
       29
      ],
      "multiple": [
       68,
       68
      ],
      "unsplittable": [
       70,
       70
      ],
      "number_rows": [
       172,
       175
      ],
      "answered_rows": [
       240,
       238
      ],
      "disp": {
       "in_doc": "12〜15",
       "not_in_doc": "87〜93",
       "unsplittable": "70",
       "number_rows": "172〜175",
       "answered_rows": "238〜240"
      }
     },
     "quote": {
      "in_doc": [
       24,
       19
      ],
      "not_in_doc": [
       90,
       96
      ],
      "no_number": [
       15,
       18
      ],
      "multiple_all_in_doc": [
       5,
       7
      ],
      "multiple_none_in_doc": [
       40,
       38
      ],
      "multiple_mixed": [
       71,
       64
      ],
      "multiple": [
       116,
       109
      ],
      "unsplittable": [
       131,
       127
      ],
      "number_rows": [
       245,
       242
      ],
      "answered_rows": [
       324,
       317
      ],
      "disp": {
       "in_doc": "19〜24",
       "not_in_doc": "90〜96",
       "unsplittable": "127〜131",
       "number_rows": "242〜245",
       "answered_rows": "317〜324"
      }
     }
    }
   },
   "doc_numbers": {
    "questions": 101,
    "near_mean": "25.9",
    "far_mean": "19.3"
   }
  }
 },
 "zero_answers": {
  "all": {
   "qwen3:8b": {
    "near": {
     "zero": [
      4,
      4
     ],
     "answered": [
      140,
      137
     ],
     "disp": {
      "zero": "4",
      "answered": "137〜140"
     }
    },
    "far": {
     "zero": [
      37,
      37
     ],
     "answered": [
      76,
      80
     ],
     "disp": {
      "zero": "37",
      "answered": "76〜80"
     }
    }
   },
   "qwen3:14b": {
    "near": {
     "zero": [
      7,
      8
     ],
     "answered": [
      116,
      121
     ],
     "disp": {
      "zero": "7〜8",
      "answered": "116〜121"
     }
    },
    "far": {
     "zero": [
      13,
      13
     ],
     "answered": [
      40,
      40
     ],
     "disp": {
      "zero": "13",
      "answered": "40"
     }
    }
   },
   "qwen3:30b": {
    "near": {
     "zero": [
      8,
      9
     ],
     "answered": [
      107,
      101
     ],
     "disp": {
      "zero": "8〜9",
      "answered": "101〜107"
     }
    },
    "far": {
     "zero": [
      24,
      27
     ],
     "answered": [
      54,
      54
     ],
     "disp": {
      "zero": "24〜27",
      "answered": "54"
     }
    }
   },
   "qwen3.5:9b": {
    "near": {
     "zero": [
      4,
      5
     ],
     "answered": [
      66,
      67
     ],
     "disp": {
      "zero": "4〜5",
      "answered": "66〜67"
     }
    },
    "far": {
     "zero": [
      5,
      4
     ],
     "answered": [
      9,
      8
     ],
     "disp": {
      "zero": "4〜5",
      "answered": "8〜9"
     }
    }
   },
   "qwen3.5:27b": {
    "near": {
     "zero": [
      2,
      1
     ],
     "answered": [
      40,
      40
     ],
     "disp": {
      "zero": "1〜2",
      "answered": "40"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      1,
      2
     ],
     "disp": {
      "zero": "0",
      "answered": "1〜2"
     }
    }
   },
   "gemma3:12b": {
    "near": {
     "zero": [
      1,
      1
     ],
     "answered": [
      69,
      67
     ],
     "disp": {
      "zero": "1",
      "answered": "67〜69"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      7,
      6
     ],
     "disp": {
      "zero": "0",
      "answered": "6〜7"
     }
    }
   },
   "gemma3:27b": {
    "near": {
     "zero": [
      2,
      2
     ],
     "answered": [
      83,
      81
     ],
     "disp": {
      "zero": "2",
      "answered": "81〜83"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      9,
      9
     ],
     "disp": {
      "zero": "0",
      "answered": "9"
     }
    }
   },
   "gemma4:12b": {
    "near": {
     "zero": [
      1,
      1
     ],
     "answered": [
      59,
      59
     ],
     "disp": {
      "zero": "1",
      "answered": "59"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      3,
      3
     ],
     "disp": {
      "zero": "0",
      "answered": "3"
     }
    }
   },
   "gemma4:26b": {
    "near": {
     "zero": [
      1,
      1
     ],
     "answered": [
      42,
      39
     ],
     "disp": {
      "zero": "1",
      "answered": "39〜42"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      2,
      3
     ],
     "disp": {
      "zero": "0",
      "answered": "2〜3"
     }
    }
   },
   "gpt-oss:20b": {
    "near": {
     "zero": [
      15,
      16
     ],
     "answered": [
      134,
      138
     ],
     "disp": {
      "zero": "15〜16",
      "answered": "134〜138"
     }
    },
    "far": {
     "zero": [
      31,
      32
     ],
     "answered": [
      140,
      139
     ],
     "disp": {
      "zero": "31〜32",
      "answered": "139〜140"
     }
    }
   },
   "gpt-oss:120b": {
    "near": {
     "zero": [
      13,
      11
     ],
     "answered": [
      120,
      123
     ],
     "disp": {
      "zero": "11〜13",
      "answered": "120〜123"
     }
    },
    "far": {
     "zero": [
      26,
      28
     ],
     "answered": [
      111,
      114
     ],
     "disp": {
      "zero": "26〜28",
      "answered": "111〜114"
     }
    }
   },
   "deepseek-r1:8b": {
    "near": {
     "zero": [
      0,
      1
     ],
     "answered": [
      71,
      69
     ],
     "disp": {
      "zero": "0〜1",
      "answered": "69〜71"
     }
    },
    "far": {
     "zero": [
      0,
      3
     ],
     "answered": [
      15,
      21
     ],
     "disp": {
      "zero": "0〜3",
      "answered": "15〜21"
     }
    }
   },
   "deepseek-r1:14b": {
    "near": {
     "zero": [
      1,
      0
     ],
     "answered": [
      92,
      90
     ],
     "disp": {
      "zero": "0〜1",
      "answered": "90〜92"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      20,
      21
     ],
     "disp": {
      "zero": "0",
      "answered": "20〜21"
     }
    }
   },
   "llama3.1:8b": {
    "near": {
     "zero": [
      0,
      0
     ],
     "answered": [
      135,
      135
     ],
     "disp": {
      "zero": "0",
      "answered": "135"
     }
    },
    "far": {
     "zero": [
      1,
      1
     ],
     "answered": [
      79,
      80
     ],
     "disp": {
      "zero": "1",
      "answered": "79〜80"
     }
    }
   },
   "mistral-small3.2:24b": {
    "near": {
     "zero": [
      2,
      2
     ],
     "answered": [
      100,
      102
     ],
     "disp": {
      "zero": "2",
      "answered": "100〜102"
     }
    },
    "far": {
     "zero": [
      1,
      1
     ],
     "answered": [
      16,
      16
     ],
     "disp": {
      "zero": "1",
      "answered": "16"
     }
    }
   },
   "phi4:14b": {
    "near": {
     "zero": [
      0,
      0
     ],
     "answered": [
      68,
      66
     ],
     "disp": {
      "zero": "0",
      "answered": "66〜68"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      5,
      6
     ],
     "disp": {
      "zero": "0",
      "answered": "5〜6"
     }
    }
   }
  },
  "excluded": {
   "qwen3:8b": {
    "near": {
     "zero": [
      4,
      4
     ],
     "answered": [
      110,
      108
     ],
     "disp": {
      "zero": "4",
      "answered": "108〜110"
     }
    },
    "far": {
     "zero": [
      33,
      33
     ],
     "answered": [
      56,
      58
     ],
     "disp": {
      "zero": "33",
      "answered": "56〜58"
     }
    }
   },
   "qwen3:14b": {
    "near": {
     "zero": [
      7,
      8
     ],
     "answered": [
      92,
      96
     ],
     "disp": {
      "zero": "7〜8",
      "answered": "92〜96"
     }
    },
    "far": {
     "zero": [
      12,
      12
     ],
     "answered": [
      30,
      30
     ],
     "disp": {
      "zero": "12",
      "answered": "30"
     }
    }
   },
   "qwen3:30b": {
    "near": {
     "zero": [
      8,
      8
     ],
     "answered": [
      81,
      75
     ],
     "disp": {
      "zero": "8",
      "answered": "75〜81"
     }
    },
    "far": {
     "zero": [
      22,
      23
     ],
     "answered": [
      43,
      40
     ],
     "disp": {
      "zero": "22〜23",
      "answered": "40〜43"
     }
    }
   },
   "qwen3.5:9b": {
    "near": {
     "zero": [
      4,
      5
     ],
     "answered": [
      48,
      49
     ],
     "disp": {
      "zero": "4〜5",
      "answered": "48〜49"
     }
    },
    "far": {
     "zero": [
      5,
      4
     ],
     "answered": [
      7,
      6
     ],
     "disp": {
      "zero": "4〜5",
      "answered": "6〜7"
     }
    }
   },
   "qwen3.5:27b": {
    "near": {
     "zero": [
      2,
      1
     ],
     "answered": [
      23,
      23
     ],
     "disp": {
      "zero": "1〜2",
      "answered": "23"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      1,
      2
     ],
     "disp": {
      "zero": "0",
      "answered": "1〜2"
     }
    }
   },
   "gemma3:12b": {
    "near": {
     "zero": [
      1,
      1
     ],
     "answered": [
      47,
      45
     ],
     "disp": {
      "zero": "1",
      "answered": "45〜47"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      4,
      3
     ],
     "disp": {
      "zero": "0",
      "answered": "3〜4"
     }
    }
   },
   "gemma3:27b": {
    "near": {
     "zero": [
      2,
      2
     ],
     "answered": [
      61,
      59
     ],
     "disp": {
      "zero": "2",
      "answered": "59〜61"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      6,
      6
     ],
     "disp": {
      "zero": "0",
      "answered": "6"
     }
    }
   },
   "gemma4:12b": {
    "near": {
     "zero": [
      1,
      1
     ],
     "answered": [
      37,
      37
     ],
     "disp": {
      "zero": "1",
      "answered": "37"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      2,
      2
     ],
     "disp": {
      "zero": "0",
      "answered": "2"
     }
    }
   },
   "gemma4:26b": {
    "near": {
     "zero": [
      1,
      1
     ],
     "answered": [
      28,
      25
     ],
     "disp": {
      "zero": "1",
      "answered": "25〜28"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      1,
      2
     ],
     "disp": {
      "zero": "0",
      "answered": "1〜2"
     }
    }
   },
   "gpt-oss:20b": {
    "near": {
     "zero": [
      15,
      16
     ],
     "answered": [
      102,
      105
     ],
     "disp": {
      "zero": "15〜16",
      "answered": "102〜105"
     }
    },
    "far": {
     "zero": [
      27,
      28
     ],
     "answered": [
      109,
      109
     ],
     "disp": {
      "zero": "27〜28",
      "answered": "109"
     }
    }
   },
   "gpt-oss:120b": {
    "near": {
     "zero": [
      13,
      11
     ],
     "answered": [
      95,
      94
     ],
     "disp": {
      "zero": "11〜13",
      "answered": "94〜95"
     }
    },
    "far": {
     "zero": [
      23,
      25
     ],
     "answered": [
      86,
      89
     ],
     "disp": {
      "zero": "23〜25",
      "answered": "86〜89"
     }
    }
   },
   "deepseek-r1:8b": {
    "near": {
     "zero": [
      0,
      1
     ],
     "answered": [
      49,
      48
     ],
     "disp": {
      "zero": "0〜1",
      "answered": "48〜49"
     }
    },
    "far": {
     "zero": [
      0,
      3
     ],
     "answered": [
      8,
      13
     ],
     "disp": {
      "zero": "0〜3",
      "answered": "8〜13"
     }
    }
   },
   "deepseek-r1:14b": {
    "near": {
     "zero": [
      1,
      0
     ],
     "answered": [
      65,
      64
     ],
     "disp": {
      "zero": "0〜1",
      "answered": "64〜65"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      12,
      12
     ],
     "disp": {
      "zero": "0",
      "answered": "12"
     }
    }
   },
   "llama3.1:8b": {
    "near": {
     "zero": [
      0,
      0
     ],
     "answered": [
      102,
      103
     ],
     "disp": {
      "zero": "0",
      "answered": "102〜103"
     }
    },
    "far": {
     "zero": [
      1,
      1
     ],
     "answered": [
      56,
      57
     ],
     "disp": {
      "zero": "1",
      "answered": "56〜57"
     }
    }
   },
   "mistral-small3.2:24b": {
    "near": {
     "zero": [
      2,
      2
     ],
     "answered": [
      70,
      72
     ],
     "disp": {
      "zero": "2",
      "answered": "70〜72"
     }
    },
    "far": {
     "zero": [
      1,
      1
     ],
     "answered": [
      10,
      10
     ],
     "disp": {
      "zero": "1",
      "answered": "10"
     }
    }
   },
   "phi4:14b": {
    "near": {
     "zero": [
      0,
      0
     ],
     "answered": [
      47,
      45
     ],
     "disp": {
      "zero": "0",
      "answered": "45〜47"
     }
    },
    "far": {
     "zero": [
      0,
      0
     ],
     "answered": [
      4,
      4
     ],
     "disp": {
      "zero": "0",
      "answered": "4"
     }
    }
   }
  }
 },
 "scoring": {
  "rows": 51072,
  "by_condition": {
   "answerable": {
    "rows": 16128,
    "judged": 2448,
    "rule_only": 13680
   },
   "near": {
    "rows": 16128,
    "judged": 5848,
    "rule_only": 10280
   },
   "far": {
    "rows": 16128,
    "judged": 2350,
    "rule_only": 13778
   },
   "nodoc": {
    "rows": 2688,
    "judged": 2554,
    "rule_only": 134
   }
  },
  "final_by_condition": {
   "answerable": {
    "correct": 15113,
    "abstain": 400,
    "hedged": 4,
    "other": 538,
    "unresolved": 73
   },
   "near": {
    "correct": 354,
    "abstain": 10806,
    "hedged": 8,
    "other": 4654,
    "unresolved": 306
   },
   "far": {
    "correct": 54,
    "abstain": 14662,
    "hedged": 1,
    "other": 1330,
    "unresolved": 81
   },
   "nodoc": {
    "correct": 130,
    "abstain": 286,
    "hedged": 2,
    "other": 2254,
    "unresolved": 16
   }
  },
  "rule_vs_judge": {
   "other|near": {
    "D": 4581,
    "A": 240,
    "B": 170,
    "E": 89
   },
   "other|answerable": {
    "A": 1576,
    "D": 525,
    "B": 1,
    "E": 14
   },
   "correct|near": {
    "A": 107,
    "D": 12
   },
   "hedged_candidate|near": {
    "D": 34,
    "B": 573,
    "A": 1,
    "C": 8
   },
   "other|far": {
    "D": 1324,
    "B": 185,
    "A": 30,
    "E": 25
   },
   "other|nodoc": {
    "D": 2248,
    "B": 97,
    "E": 7,
    "A": 75,
    "C": 2
   },
   "hedged_candidate|nodoc": {
    "B": 64,
    "D": 2
   },
   "correct|nodoc": {
    "A": 55,
    "D": 4
   },
   "hedged_candidate|far": {
    "B": 755,
    "D": 6
   },
   "unresolved|near": {
    "D": 27,
    "A": 6
   },
   "unresolved|answerable": {
    "A": 280,
    "B": 7,
    "C": 4,
    "D": 9,
    "E": 2
   },
   "unresolved|far": {
    "C": 1
   },
   "hedged_candidate|answerable": {
    "B": 25,
    "D": 4,
    "A": 1
   },
   "correct|far": {
    "A": 24
   }
  },
  "judge_labels": {
   "D": 8776,
   "A": 2395,
   "B": 1877,
   "E": 137,
   "C": 15
  },
  "judged": 13200,
  "answered_rows": {
   "judged": 8791,
   "rule_only": 0
  },
  "rule_only": 37872,
  "rule_labels": {
   "correct": 13458,
   "abstain": 24277,
   "other": 11189,
   "hedged_candidate": 1473,
   "unresolved": 675
  },
  "to_judge_rows": 13200,
  "to_judge_pairs": 7126,
  "to_judge_reasons": {
   "nearfar_other": 6644,
   "answerable_other": 2116,
   "nearfar_correct": 143,
   "hedged_candidate": 1473,
   "nodoc_other": 2429,
   "nodoc_correct": 59,
   "unresolved": 336
  },
  "to_judge_missing_label": 0,
  "range_guard_rows": 0,
  "judge": {
   "model": "gpt-oss:120b",
   "think": "medium",
   "prompt_version": 3,
   "options": {
    "temperature": 0,
    "seed": 42,
    "num_predict": 2000,
    "num_ctx": 4096
   },
   "note": "同じ問いの同じ出力は 1 組として 1 回だけ判定し、元の行すべてに配った。判定は A〜E の 1 文字。"
  },
  "audit": {
   "judge_pairs_sampled": 200,
   "judge_errors": 3,
   "judge_error_rate": "1.5",
   "judge_seed": 20261112,
   "rule_rows_sampled": 80,
   "rule_errors": 0,
   "rule_error_rate": "0.0",
   "note": "判定役が付けた区分ごとにほぼ同じ数（47〜48 組。母数が 11 組の区分 C は全部）を抜いた 200 組を読んだ。誤り＝最終の区分（正答・辞退・答えを出した・答えも辞退も無い）が変わる取り違え。境界＝読む人によって区分が分かれる組。「断りながら答えた」と「誤答」の取り違えは最終の集計を変えないので誤りに数えない（0 組）。",
   "source": "audit.json",
   "pass_line": 3,
   "reader": "Claude Fable 5.2",
   "judge": {
    "read": 200,
    "population": 7126,
    "errors": 3,
    "boundary": 14,
    "error_rate": "1.5",
    "error_boundary_rate": "8.5",
    "weighted_error_rate": "0.3",
    "weighted_error_boundary_rate": "6.3",
    "seed": 20261112,
    "by_class": {
     "A": {
      "population": 980,
      "read": 47,
      "errors": 1,
      "boundary": 3
     },
     "B": {
      "population": 1355,
      "read": 47,
      "errors": 0,
      "boundary": 2
     },
     "C": {
      "population": 11,
      "read": 11,
      "errors": 1,
      "boundary": 2
     },
     "D": {
      "population": 4692,
      "read": 48,
      "errors": 0,
      "boundary": 3
     },
     "E": {
      "population": 88,
      "read": 47,
      "errors": 1,
      "boundary": 4
     }
    },
    "cd_mixups": 0,
    "pass": true,
    "wilson95": [
     "0.5",
     "4.3"
    ],
    "wilson95_disp": "0.5〜4.3"
   },
   "rule": {
    "read": 80,
    "population": 37533,
    "errors": 0,
    "boundary": 0,
    "error_rate": "0.0",
    "error_boundary_rate": "0.0",
    "weighted_error_rate": "0.0",
    "weighted_error_boundary_rate": "0.0",
    "seed": 20261112,
    "by_class": {
     "abstain": {
      "population": 24277,
      "read": 50,
      "errors": 0,
      "boundary": 0
     },
     "answerable_correct": {
      "population": 13256,
      "read": 30,
      "errors": 0,
      "boundary": 0
     }
    }
   }
  }
 }
}