{
 "bench_id": "b013-gazou",
 "slug": "gazou-2026-11-03",
 "title": "レシート・グラフ・表の画像から数字を読む（4AI・6課題・各3回）",
 "field": "画像・写真の読み取り",
 "field_key": "gazou",
 "round": 1,
 "run_date": "2026-11-03",
 "timezone": "Asia/Tokyo",
 "version": "v1",
 "conductor": "AInformation編集部",
 "funder": "AInformation（自社負担）",
 "sponsor": null,
 "method": {
  "tasks_n": 6,
  "repeats": 3,
  "ais_n": 4,
  "trials_total": 72,
  "trials_valid": 72,
  "excluded": [],
  "new_chat_each_time": true,
  "order_rotated": true,
  "order_by_repeat": {
   "1": [
    "ChatGPT",
    "Gemini",
    "Claude",
    "Copilot"
   ],
   "2": [
    "Gemini",
    "Claude",
    "Copilot",
    "ChatGPT"
   ],
   "3": [
    "Claude",
    "Copilot",
    "ChatGPT",
    "Gemini"
   ]
  },
  "timeout_seconds": 300,
  "scoring": "機械採点のみ（AIに採点させていない）",
  "materials_generated_at": "2026-11-02",
  "materials_note": "自作のレシート画像・棒グラフ画像・少し傾けた表の画像。元の数は作るときに決めてある",
  "counted_outcomes": [
   "scored",
   "refused",
   "timeout"
  ],
  "excluded_outcomes": [
   "limit",
   "our_error",
   "human_check"
  ],
  "answer_cleanup": "画面から答えを読み取るとき、AIによっては読み上げ用の1行や考えている途中の要約が答えと同じ枠に入る。採点の前に「答えの先頭にあって、あとでそっくり同じ行がもう一度出てくる」ところまでを落とす。4AIとも同じ処理をする。落とす前の答えは answers/ にそのまま置いてある",
  "csv_url": "/data/research/bench/gazou-2026-11-03/latest.csv"
 },
 "ais": [
  {
   "name": "ChatGPT",
   "plan": "ChatGPT Pro",
   "model_shown": "GPT-6.1 Sol 中",
   "checked_at": "2026-11-02 21:03"
  },
  {
   "name": "Gemini",
   "plan": "Google AI Pro",
   "model_shown": "Flash",
   "checked_at": "2026-11-02 21:03"
  },
  {
   "name": "Claude",
   "plan": "Claude Max",
   "model_shown": "Opus 4.8  高",
   "checked_at": "2026-11-02 21:03"
  },
  {
   "name": "Copilot",
   "plan": "Microsoft 365 Personal",
   "model_shown": null,
   "checked_at": "2026-11-02 21:03"
  }
 ],
 "summary": {
  "headline": "6課題を各3回ずつ投げたところ、正解率が一番高かったのはClaudeで18/18試行の100.0%だった（2位はChatGPTの72.2%）",
  "winner": "Claude",
  "note": "1回の検証の結果。日や課題が変われば順位は変わる"
 },
 "scores": [
  {
   "ai": "ChatGPT",
   "correct": 13,
   "trials": 18,
   "accuracy": 0.7222,
   "accuracy_display": 72.2,
   "seconds_median": 25.4,
   "seconds_min": 20.4,
   "seconds_max": 48.3,
   "consistency": 0.8333,
   "consistency_display": 83.3,
   "source_alive": null,
   "source_alive_display": null,
   "instruction_follow": 1.0,
   "instruction_follow_display": 100.0,
   "failures": {
    "refused": 0,
    "timeout": 4,
    "limit": 0,
    "our_error": 0,
    "human_check": 0
   }
  },
  {
   "ai": "Gemini",
   "correct": 7,
   "trials": 18,
   "accuracy": 0.3889,
   "accuracy_display": 38.9,
   "seconds_median": 69.2,
   "seconds_min": 19.0,
   "seconds_max": 204.9,
   "consistency": 1.0,
   "consistency_display": 100.0,
   "source_alive": null,
   "source_alive_display": null,
   "instruction_follow": 0.625,
   "instruction_follow_display": 62.5,
   "failures": {
    "refused": 0,
    "timeout": 10,
    "limit": 0,
    "our_error": 0,
    "human_check": 0
   }
  },
  {
   "ai": "Claude",
   "correct": 18,
   "trials": 18,
   "accuracy": 1.0,
   "accuracy_display": 100.0,
   "seconds_median": 13.9,
   "seconds_min": 13.8,
   "seconds_max": 17.1,
   "consistency": 1.0,
   "consistency_display": 100.0,
   "source_alive": null,
   "source_alive_display": null,
   "instruction_follow": 0.1667,
   "instruction_follow_display": 16.7,
   "failures": {
    "refused": 0,
    "timeout": 0,
    "limit": 0,
    "our_error": 0,
    "human_check": 0
   }
  },
  {
   "ai": "Copilot",
   "correct": 0,
   "trials": 18,
   "accuracy": 0.0,
   "accuracy_display": 0.0,
   "seconds_median": 14.0,
   "seconds_min": 13.8,
   "seconds_max": 17.1,
   "consistency": 1.0,
   "consistency_display": 100.0,
   "source_alive": null,
   "source_alive_display": null,
   "instruction_follow": 0.5,
   "instruction_follow_display": 50.0,
   "failures": {
    "refused": 0,
    "timeout": 0,
    "limit": 0,
    "our_error": 0,
    "human_check": 0
   }
  }
 ],
 "tasks": [
  {
   "task_id": "t1",
   "level": "易",
   "prompt": "添付したレシートの画像から、3つの数を読み取ってください。\n\n決まり\n・答えはちょうど3行。小計: ◯／消費税: ◯／合計: ◯ の順で書く\n・数は半角で書く。円記号とカンマは付けなくてよい。説明は書かない",
   "scorer": "exact_number",
   "answer_key": "（機械採点 exact_number）小計＝2316（誤差±0）／消費税＝185（誤差±0）／合計＝2501（誤差±0）",
   "materials": [
    "/data/research/bench/gazou-2026-11-03/materials/receipt.png"
   ],
   "per_ai": [
    {
     "ai": "ChatGPT",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 35.8,
       "chars": 26,
       "why": "数値すべて一致：小計 ○（正解2316）／消費税 ○（正解185）／合計 ○（正解2501）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t1_chatgpt_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/chatgpt_01_t1.png"
      },
      {
       "n": 2,
       "ok": true,
       "outcome": "scored",
       "seconds": 29.7,
       "chars": 26,
       "why": "数値すべて一致：小計 ○（正解2316）／消費税 ○（正解185）／合計 ○（正解2501）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t1_chatgpt_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": true,
       "outcome": "scored",
       "seconds": 20.5,
       "chars": 26,
       "why": "数値すべて一致：小計 ○（正解2316）／消費税 ○（正解185）／合計 ○（正解2501）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t1_chatgpt_3.txt",
       "shot": null
      }
     ]
    },
    {
     "ai": "Gemini",
     "trials": [
      {
       "n": 1,
       "ok": false,
       "outcome": "scored",
       "seconds": 19.2,
       "chars": 26,
       "why": "数値が違う：小計 ×（正解2316・小計 の行が無い）／消費税 ×（正解185・税 の行が無い）／合計 ×（正解2501・合計 の行が無い）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t1_gemini_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/gemini_01_t1.png"
      },
      {
       "n": 2,
       "ok": false,
       "outcome": "timeout",
       "seconds": 302.6,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "timeout",
       "seconds": 302.2,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      }
     ]
    },
    {
     "ai": "Claude",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 60,
       "why": "数値すべて一致：小計 ○（正解2316）／消費税 ○（正解185）／合計 ○（正解2501）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t1_claude_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/claude_01_t1.png"
      },
      {
       "n": 2,
       "ok": true,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 60,
       "why": "数値すべて一致：小計 ○（正解2316）／消費税 ○（正解185）／合計 ○（正解2501）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t1_claude_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": true,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 92,
       "why": "数値すべて一致：小計 ○（正解2316）／消費税 ○（正解185）／合計 ○（正解2501）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t1_claude_3.txt",
       "shot": null
      }
     ]
    },
    {
     "ai": "Copilot",
     "trials": [
      {
       "n": 1,
       "ok": false,
       "outcome": "scored",
       "seconds": 14.0,
       "chars": 46,
       "why": "数値が違う：小計 ×（正解2316・小計 の行が無い）／消費税 ×（正解185・税 の行が無い）／合計 ×（正解2501・合計 の行が無い）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t1_copilot_1.txt",
       "shot": null
      },
      {
       "n": 2,
       "ok": false,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 46,
       "why": "数値が違う：小計 ×（正解2316・小計 の行が無い）／消費税 ×（正解185・税 の行が無い）／合計 ×（正解2501・合計 の行が無い）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t1_copilot_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 46,
       "why": "数値が違う：小計 ×（正解2316・小計 の行が無い）／消費税 ×（正解185・税 の行が無い）／合計 ×（正解2501・合計 の行が無い）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t1_copilot_3.txt",
       "shot": null
      }
     ]
    }
   ]
  },
  {
   "task_id": "t2",
   "level": "易",
   "prompt": "添付したレシートの画像から、お釣りの金額を読み取ってください。\n\n決まり\n・答えはちょうど1行。お釣り: ◯ の形で書く\n・数は半角で書く。説明は書かない",
   "scorer": "exact_number",
   "answer_key": "（機械採点 exact_number）お釣り＝499（誤差±0）",
   "materials": [
    "/data/research/bench/gazou-2026-11-03/materials/receipt.png"
   ],
   "per_ai": [
    {
     "ai": "ChatGPT",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 24.1,
       "chars": 8,
       "why": "数値すべて一致：お釣り ○（正解499）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t2_chatgpt_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/chatgpt_02_t2.png"
      },
      {
       "n": 2,
       "ok": true,
       "outcome": "scored",
       "seconds": 20.4,
       "chars": 8,
       "why": "数値すべて一致：お釣り ○（正解499）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t2_chatgpt_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": true,
       "outcome": "scored",
       "seconds": 20.4,
       "chars": 8,
       "why": "数値すべて一致：お釣り ○（正解499）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t2_chatgpt_3.txt",
       "shot": null
      }
     ]
    },
    {
     "ai": "Gemini",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 59.7,
       "chars": 23,
       "why": "数値すべて一致：お釣り ○（正解499）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t2_gemini_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/gemini_02_t2.png"
      },
      {
       "n": 2,
       "ok": false,
       "outcome": "timeout",
       "seconds": 302.3,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "timeout",
       "seconds": 302.1,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      }
     ]
    },
    {
     "ai": "Claude",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 14.1,
       "chars": 42,
       "why": "数値すべて一致：お釣り ○（正解499）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t2_claude_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/claude_02_t2.png"
      },
      {
       "n": 2,
       "ok": true,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 42,
       "why": "数値すべて一致：お釣り ○（正解499）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t2_claude_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": true,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 42,
       "why": "数値すべて一致：お釣り ○（正解499）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t2_claude_3.txt",
       "shot": null
      }
     ]
    },
    {
     "ai": "Copilot",
     "trials": [
      {
       "n": 1,
       "ok": false,
       "outcome": "scored",
       "seconds": 14.1,
       "chars": 46,
       "why": "数値が違う：お釣り ×（正解499・釣 の行が無い）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t2_copilot_1.txt",
       "shot": null
      },
      {
       "n": 2,
       "ok": false,
       "outcome": "scored",
       "seconds": 14.1,
       "chars": 46,
       "why": "数値が違う：お釣り ×（正解499・釣 の行が無い）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t2_copilot_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "scored",
       "seconds": 13.8,
       "chars": 46,
       "why": "数値が違う：お釣り ×（正解499・釣 の行が無い）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t2_copilot_3.txt",
       "shot": null
      }
     ]
    }
   ]
  },
  {
   "task_id": "t3",
   "level": "中",
   "prompt": "添付したレシートの画像から、買った品物を全部書き出してください。\n\n決まり\n・1品につき1行。行の先頭は ・ にする。品名と金額を書く\n・小計・消費税・合計・お預り・お釣りの行は書かない",
   "scorer": "set_match",
   "answer_key": "（機械採点 set_match）牛乳 1000ml［牛乳＋314］／ヨーグルト 400g［ヨーグルト＋184］／うどん 3玉［うどん＋184］／鶏むね肉 2枚［鶏むね肉＋454］／洗剤 詰め替え［洗剤＋496］／コーヒー 200g［コーヒー＋684］　作り足しは0件まで",
   "materials": [
    "/data/research/bench/gazou-2026-11-03/materials/receipt.png"
   ],
   "per_ai": [
    {
     "ai": "ChatGPT",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 27.2,
       "chars": 89,
       "why": "6件すべて一致・作り足し0件",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t3_chatgpt_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/chatgpt_03_t3.png"
      },
      {
       "n": 2,
       "ok": true,
       "outcome": "scored",
       "seconds": 32.8,
       "chars": 89,
       "why": "6件すべて一致・作り足し0件",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t3_chatgpt_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "timeout",
       "seconds": 300.6,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      }
     ]
    },
    {
     "ai": "Gemini",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 189.8,
       "chars": 89,
       "why": "6件すべて一致・作り足し0件",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t3_gemini_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/gemini_03_t3.png"
      },
      {
       "n": 2,
       "ok": true,
       "outcome": "scored",
       "seconds": 19.0,
       "chars": 89,
       "why": "6件すべて一致・作り足し0件",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t3_gemini_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "timeout",
       "seconds": 302.1,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      }
     ]
    },
    {
     "ai": "Claude",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 17.0,
       "chars": 198,
       "why": "6件すべて一致・作り足し0件",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t3_claude_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/claude_03_t3.png"
      },
      {
       "n": 2,
       "ok": true,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 149,
       "why": "6件すべて一致・作り足し0件",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t3_claude_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": true,
       "outcome": "scored",
       "seconds": 13.8,
       "chars": 163,
       "why": "6件すべて一致・作り足し0件",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t3_claude_3.txt",
       "shot": null
      }
     ]
    },
    {
     "ai": "Copilot",
     "trials": [
      {
       "n": 1,
       "ok": false,
       "outcome": "scored",
       "seconds": 14.1,
       "chars": 46,
       "why": "6件中0件一致・漏れ 牛乳 1000ml／ヨーグルト 400g／うどん 3玉／鶏むね肉 2枚／洗剤 詰め替え／コーヒー 200g・作り足し1件",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t3_copilot_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/copilot_03_t3.png"
      },
      {
       "n": 2,
       "ok": false,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 46,
       "why": "6件中0件一致・漏れ 牛乳 1000ml／ヨーグルト 400g／うどん 3玉／鶏むね肉 2枚／洗剤 詰め替え／コーヒー 200g・作り足し1件",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t3_copilot_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 46,
       "why": "6件中0件一致・漏れ 牛乳 1000ml／ヨーグルト 400g／うどん 3玉／鶏むね肉 2枚／洗剤 詰め替え／コーヒー 200g・作り足し1件",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t3_copilot_3.txt",
       "shot": null
      }
     ]
    }
   ]
  },
  {
   "task_id": "t4",
   "level": "中",
   "prompt": "添付した棒グラフの画像で、棒が一番高い月はどれですか。\n\n決まり\n・答えはちょうど1行。◯月 の形で書く\n・数値と説明は書かない",
   "scorer": "contains_all",
   "answer_key": "（機械採点 contains_all）いちばん高い月＝6月",
   "materials": [
    "/data/research/bench/gazou-2026-11-03/materials/chart.png"
   ],
   "per_ai": [
    {
     "ai": "ChatGPT",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 26.7,
       "chars": 2,
       "why": "1項目すべてあり",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t4_chatgpt_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/chatgpt_04_t4.png"
      },
      {
       "n": 2,
       "ok": true,
       "outcome": "scored",
       "seconds": 48.3,
       "chars": 2,
       "why": "1項目すべてあり",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t4_chatgpt_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "timeout",
       "seconds": 300.8,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      }
     ]
    },
    {
     "ai": "Gemini",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 61.7,
       "chars": 2,
       "why": "1項目すべてあり",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t4_gemini_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/gemini_04_t4.png"
      },
      {
       "n": 2,
       "ok": false,
       "outcome": "timeout",
       "seconds": 302.2,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      },
      {
       "n": 3,
       "ok": true,
       "outcome": "scored",
       "seconds": 76.7,
       "chars": 15,
       "why": "1項目すべてあり",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t4_gemini_3.txt",
       "shot": null
      }
     ]
    },
    {
     "ai": "Claude",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 30,
       "why": "1項目すべてあり",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t4_claude_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/claude_04_t4.png"
      },
      {
       "n": 2,
       "ok": true,
       "outcome": "scored",
       "seconds": 13.8,
       "chars": 30,
       "why": "1項目すべてあり",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t4_claude_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": true,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 30,
       "why": "1項目すべてあり",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t4_claude_3.txt",
       "shot": null
      }
     ]
    },
    {
     "ai": "Copilot",
     "trials": [
      {
       "n": 1,
       "ok": false,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 46,
       "why": "1項目中0項目あり・足りない いちばん高い月",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t4_copilot_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/copilot_04_t4.png"
      },
      {
       "n": 2,
       "ok": false,
       "outcome": "scored",
       "seconds": 14.0,
       "chars": 46,
       "why": "1項目中0項目あり・足りない いちばん高い月",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t4_copilot_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "scored",
       "seconds": 14.0,
       "chars": 46,
       "why": "1項目中0項目あり・足りない いちばん高い月",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t4_copilot_3.txt",
       "shot": null
      }
     ]
    }
   ]
  },
  {
   "task_id": "t5",
   "level": "難",
   "prompt": "添付した棒グラフの画像から、月ごとの数値を全部読み取ってください。\n\n決まり\n・1か月につき1行。◯月: ◯◯◯ の形で、左から順に書く\n・数は半角で書く。説明は書かない",
   "scorer": "exact_number",
   "answer_key": "（機械採点 exact_number）1月＝5500（誤差±0）／2月＝5500（誤差±0）／3月＝8200（誤差±0）／4月＝12300（誤差±0）／5月＝17800（誤差±0）／6月＝24700（誤差±0）",
   "materials": [
    "/data/research/bench/gazou-2026-11-03/materials/chart.png"
   ],
   "per_ai": [
    {
     "ai": "ChatGPT",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 20.5,
       "chars": 56,
       "why": "数値すべて一致：1月 ○（正解5500）／2月 ○（正解5500）／3月 ○（正解8200）／4月 ○（正解12300）／5月 ○（正解17800）／6月 ○（正解24700）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t5_chatgpt_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/chatgpt_05_t5.png"
      },
      {
       "n": 2,
       "ok": true,
       "outcome": "scored",
       "seconds": 26.6,
       "chars": 56,
       "why": "数値すべて一致：1月 ○（正解5500）／2月 ○（正解5500）／3月 ○（正解8200）／4月 ○（正解12300）／5月 ○（正解17800）／6月 ○（正解24700）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t5_chatgpt_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "timeout",
       "seconds": 300.8,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      }
     ]
    },
    {
     "ai": "Gemini",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 204.9,
       "chars": 62,
       "why": "数値すべて一致：1月 ○（正解5500）／2月 ○（正解5500）／3月 ○（正解8200）／4月 ○（正解12300）／5月 ○（正解17800）／6月 ○（正解24700）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t5_gemini_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/gemini_05_t5.png"
      },
      {
       "n": 2,
       "ok": false,
       "outcome": "timeout",
       "seconds": 302.1,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "timeout",
       "seconds": 302.3,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      }
     ]
    },
    {
     "ai": "Claude",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 90,
       "why": "数値すべて一致：1月 ○（正解5500）／2月 ○（正解5500）／3月 ○（正解8200）／4月 ○（正解12300）／5月 ○（正解17800）／6月 ○（正解24700）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t5_claude_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/claude_05_t5.png"
      },
      {
       "n": 2,
       "ok": true,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 90,
       "why": "数値すべて一致：1月 ○（正解5500）／2月 ○（正解5500）／3月 ○（正解8200）／4月 ○（正解12300）／5月 ○（正解17800）／6月 ○（正解24700）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t5_claude_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": true,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 98,
       "why": "数値すべて一致：1月 ○（正解5500）／2月 ○（正解5500）／3月 ○（正解8200）／4月 ○（正解12300）／5月 ○（正解17800）／6月 ○（正解24700）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t5_claude_3.txt",
       "shot": null
      }
     ]
    },
    {
     "ai": "Copilot",
     "trials": [
      {
       "n": 1,
       "ok": false,
       "outcome": "scored",
       "seconds": 14.0,
       "chars": 46,
       "why": "数値が違う：1月 ×（正解5500・1月 の行が無い）／2月 ×（正解5500・2月 の行が無い）／3月 ×（正解8200・3月 の行が無い）／4月 ×（正解12300・4月 の行が無い）／5月 ×（正解17800・5月 の行が無い）／6月 ×（正解24700・6月 の行が無い）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t5_copilot_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/copilot_05_t5.png"
      },
      {
       "n": 2,
       "ok": false,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 46,
       "why": "数値が違う：1月 ×（正解5500・1月 の行が無い）／2月 ×（正解5500・2月 の行が無い）／3月 ×（正解8200・3月 の行が無い）／4月 ×（正解12300・4月 の行が無い）／5月 ×（正解17800・5月 の行が無い）／6月 ×（正解24700・6月 の行が無い）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t5_copilot_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "scored",
       "seconds": 13.9,
       "chars": 46,
       "why": "数値が違う：1月 ×（正解5500・1月 の行が無い）／2月 ×（正解5500・2月 の行が無い）／3月 ×（正解8200・3月 の行が無い）／4月 ×（正解12300・4月 の行が無い）／5月 ×（正解17800・5月 の行が無い）／6月 ×（正解24700・6月 の行が無い）",
       "instruction_follow": false,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t5_copilot_3.txt",
       "shot": null
      }
     ]
    }
   ]
  },
  {
   "task_id": "t6",
   "level": "難",
   "prompt": "添付した表の画像（少し傾いています）から、商品Aの列の数値を全部読み取ってください。\n\n決まり\n・1行につき1つ。月: ◯◯◯ の形で、上から順に書く\n・数は半角で書く。説明は書かない",
   "scorer": "exact_number",
   "answer_key": "（機械採点 exact_number）2025-07＝32900（誤差±0）／2025-08＝35600（誤差±0）／2025-09＝23300（誤差±0）／2025-10＝11000（誤差±0）",
   "materials": [
    "/data/research/bench/gazou-2026-11-03/materials/table_photo.png"
   ],
   "per_ai": [
    {
     "ai": "ChatGPT",
     "trials": [
      {
       "n": 1,
       "ok": false,
       "outcome": "scored",
       "seconds": 20.6,
       "chars": 40,
       "why": "数値が違う：2025-07 ×（正解32900・2025-07 の行が無い）／2025-08 ×（正解35600・2025-08 の行が無い）／2025-09 ×（正解23300・2025-09 の行が無い）／2025-10 ×（正解11000・2025-10 の行が無い）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t6_chatgpt_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/chatgpt_06_t6.png"
      },
      {
       "n": 2,
       "ok": true,
       "outcome": "scored",
       "seconds": 20.5,
       "chars": 59,
       "why": "数値すべて一致：2025-07 ○（正解32900）／2025-08 ○（正解35600）／2025-09 ○（正解23300）／2025-10 ○（正解11000）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t6_chatgpt_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "timeout",
       "seconds": 301.2,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      }
     ]
    },
    {
     "ai": "Gemini",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 134.9,
       "chars": 63,
       "why": "数値すべて一致：2025-07 ○（正解32900）／2025-08 ○（正解35600）／2025-09 ○（正解23300）／2025-10 ○（正解11000）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t6_gemini_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/gemini_06_t6.png"
      },
      {
       "n": 2,
       "ok": false,
       "outcome": "timeout",
       "seconds": 302.1,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "timeout",
       "seconds": 302.5,
       "chars": 0,
       "why": "時間切れ（制限時間まで答えが止まらなかった）",
       "instruction_follow": null,
       "answer_url": null,
       "shot": null
      }
     ]
    },
    {
     "ai": "Claude",
     "trials": [
      {
       "n": 1,
       "ok": true,
       "outcome": "scored",
       "seconds": 17.1,
       "chars": 124,
       "why": "数値すべて一致：2025-07 ○（正解32900）／2025-08 ○（正解35600）／2025-09 ○（正解23300）／2025-10 ○（正解11000）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t6_claude_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/claude_06_t6.png"
      },
      {
       "n": 2,
       "ok": true,
       "outcome": "scored",
       "seconds": 17.0,
       "chars": 126,
       "why": "数値すべて一致：2025-07 ○（正解32900）／2025-08 ○（正解35600）／2025-09 ○（正解23300）／2025-10 ○（正解11000）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t6_claude_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": true,
       "outcome": "scored",
       "seconds": 16.9,
       "chars": 128,
       "why": "数値すべて一致：2025-07 ○（正解32900）／2025-08 ○（正解35600）／2025-09 ○（正解23300）／2025-10 ○（正解11000）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t6_claude_3.txt",
       "shot": null
      }
     ]
    },
    {
     "ai": "Copilot",
     "trials": [
      {
       "n": 1,
       "ok": false,
       "outcome": "scored",
       "seconds": 14.0,
       "chars": 46,
       "why": "数値が違う：2025-07 ×（正解32900・2025-07 の行が無い）／2025-08 ×（正解35600・2025-08 の行が無い）／2025-09 ×（正解23300・2025-09 の行が無い）／2025-10 ×（正解11000・2025-10 の行が無い）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t6_copilot_1.txt",
       "shot": "/data/research/bench/gazou-2026-11-03/shots/copilot_06_t6.png"
      },
      {
       "n": 2,
       "ok": false,
       "outcome": "scored",
       "seconds": 17.1,
       "chars": 46,
       "why": "数値が違う：2025-07 ×（正解32900・2025-07 の行が無い）／2025-08 ×（正解35600・2025-08 の行が無い）／2025-09 ×（正解23300・2025-09 の行が無い）／2025-10 ×（正解11000・2025-10 の行が無い）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t6_copilot_2.txt",
       "shot": null
      },
      {
       "n": 3,
       "ok": false,
       "outcome": "scored",
       "seconds": 14.0,
       "chars": 46,
       "why": "数値が違う：2025-07 ×（正解32900・2025-07 の行が無い）／2025-08 ×（正解35600・2025-08 の行が無い）／2025-09 ×（正解23300・2025-09 の行が無い）／2025-10 ×（正解11000・2025-10 の行が無い）",
       "instruction_follow": true,
       "answer_url": "/data/research/bench/gazou-2026-11-03/answers/t6_copilot_3.txt",
       "shot": null
      }
     ]
    }
   ]
  }
 ],
 "limits": [
  "1日1回の測定である。日や課題が変われば順位は変わる",
  "プランは各AIの有料版（ChatGPT Pro／Google AI Pro／Claude Max／Microsoft 365 Personal）。無料版の結果ではない",
  "既定のモデル・既定のモードだけで測っている（Deep Research などは使っていない）",
  "課題は架空の株式会社サンプル商事の自作データ。実在の企業のデータでの結果ではない",
  "機械で採点できる課題だけを扱っている。文章のうまさ・読みやすさは測っていない",
  "ブラウザで人が使うのと同じ画面から測っている。APIの結果ではない",
  "画面に出ているモデル名を読み取れないAIがある回は、その欄を空（null）にしている。読み取れた回はそのまま載せている"
 ],
 "license": "CC BY 4.0",
 "attribution": "出典として AInformation調べ と、使ったページのURL・測定日を書いてください。",
 "page_url": "https://ainformation.jp/research/bench/gazou-2026-11-03"
}