{
  "url": "https://www.aibattle.space/models/claude-opus-5",
  "slug": "claude-opus-5",
  "name": "Claude Opus 5 (Adaptive Reasoning, Max Effort)",
  "creator": "Anthropic",
  "rebuilt": "2026-09-19",
  "placements": [
    {
      "dataset": "AA-Briefcase Elo",
      "rank": 2,
      "total": 20,
      "value": 1644.9
    },
    {
      "dataset": "GDPval-AA v2 Leaderboard",
      "rank": 2,
      "total": 20,
      "value": 1735.09
    },
    {
      "dataset": "AA-Briefcase Elo",
      "rank": 2,
      "total": 20,
      "value": 1644.9
    },
    {
      "dataset": "Artificial Analysis Intelligence Index by Open Weights / Proprietary",
      "rank": 3,
      "total": 20,
      "value": 50.7001865797629
    },
    {
      "dataset": "Artificial Analysis Intelligence Index by Open Weights / Proprietary",
      "rank": 3,
      "total": 20,
      "value": 50.7001865797629
    },
    {
      "dataset": "Artificial Analysis Intelligence Index",
      "rank": 3,
      "total": 20,
      "value": 50.7001865797629
    },
    {
      "dataset": "Artificial Analysis Finance & Accounting Index",
      "rank": 3,
      "total": 20,
      "value": 54.879570063518685
    },
    {
      "dataset": "Artificial Analysis Intelligence Index",
      "rank": 3,
      "total": 20,
      "value": 50.7001865797629
    },
    {
      "dataset": "AA-Briefcase Elo",
      "rank": 3,
      "total": 20,
      "value": 1644.9
    },
    {
      "dataset": "GDPval-AA v2 Leaderboard",
      "rank": 3,
      "total": 20,
      "value": 1735.09
    },
    {
      "dataset": "AA-AnalystAgent pass^5",
      "rank": 2,
      "total": 11,
      "value": 0.5375
    },
    {
      "dataset": "AA-Omniscience Index",
      "rank": 4,
      "total": 20,
      "value": 37.0666666666667
    },
    {
      "dataset": "AA-Omniscience Index",
      "rank": 4,
      "total": 20,
      "value": 37.0666666666667
    },
    {
      "dataset": "Humanity's Last Exam: Score",
      "rank": 5,
      "total": 20,
      "value": 0.548656163113994
    },
    {
      "dataset": "AA-Omniscience Index: Token Usage",
      "rank": 5,
      "total": 20,
      "value": 1025626
    },
    {
      "dataset": "Intelligence",
      "rank": 3,
      "total": 11,
      "value": 50.7001865797629
    },
    {
      "dataset": "Intelligence",
      "rank": 3,
      "total": 11,
      "value": 50.7001865797629
    },
    {
      "dataset": "AA-Briefcase Tool Calls Breakdown, Avg per Task",
      "rank": 6,
      "total": 20,
      "value": 58.78021978021978
    },
    {
      "dataset": "AA-Briefcase Rubric Pass Rate by File Type (Normalized)",
      "rank": 6,
      "total": 20,
      "value": 0.8589743589743589
    },
    {
      "dataset": "SciCode: Output Tokens per Task",
      "rank": 6,
      "total": 20,
      "value": 867.0208333333334
    },
    {
      "dataset": "Mean Turns per Task",
      "rank": 7,
      "total": 20,
      "value": 102.73626373626374
    },
    {
      "dataset": "Terminal-Bench v4.0: Score",
      "rank": 8,
      "total": 20,
      "value": 0.48989898989899
    },
    {
      "dataset": "AA-Omniscience Accuracy",
      "rank": 8,
      "total": 20,
      "value": 0.6086666666666667
    },
    {
      "dataset": "GDPval-AA v2: Average Turns per Task",
      "rank": 8,
      "total": 20,
      "value": 60.4703196347032
    },
    {
      "dataset": "MMMU-Pro: Token Usage",
      "rank": 8,
      "total": 19,
      "value": 1207066
    },
    {
      "dataset": "MMMU-Pro: Score",
      "rank": 8,
      "total": 19,
      "value": 0.847398843930636
    },
    {
      "dataset": "AA-Omniscience Index: Score",
      "rank": 9,
      "total": 20,
      "value": 37.0666666666667
    },
    {
      "dataset": "SciCode: Time per Task",
      "rank": 10,
      "total": 20,
      "value": 0.8062923893587501
    },
    {
      "dataset": "AA-LCR v1.1: Output Tokens per Task",
      "rank": 11,
      "total": 20,
      "value": 594.52
    },
    {
      "dataset": "Context Window",
      "rank": 12,
      "total": 20,
      "value": 1000000
    },
    {
      "dataset": "End-to-End Response Time",
      "rank": 15,
      "total": 20,
      "value": 46.504496617
    },
    {
      "dataset": "Latency: Time To First Answer Token",
      "rank": 15,
      "total": 20,
      "value": 46.504496617
    },
    {
      "dataset": "SciCode: Score",
      "rank": 15,
      "total": 20,
      "value": 0.563657407407407
    },
    {
      "dataset": "AA-LCR v1.1: Time per Task",
      "rank": 16,
      "total": 20,
      "value": 0.35886579019256687
    },
    {
      "dataset": "𝜏³-Banking: Score",
      "rank": 16,
      "total": 20,
      "value": 0.420618556701031
    },
    {
      "dataset": "AA-Omniscience Hallucination Rate",
      "rank": 17,
      "total": 20,
      "value": 0.6081771720613288
    },
    {
      "dataset": "Speed",
      "rank": 10,
      "total": 11,
      "value": 50.072458504562
    },
    {
      "dataset": "Cost per Task",
      "rank": 10,
      "total": 11,
      "value": 5.858396237036018
    },
    {
      "dataset": "Speed",
      "rank": 10,
      "total": 11,
      "value": 50.072458504562
    },
    {
      "dataset": "Cost per Task",
      "rank": 10,
      "total": 11,
      "value": 5.858396237036018
    },
    {
      "dataset": "MMMU-Pro: Total Cost to Run",
      "rank": 18,
      "total": 19,
      "value": 6.03533
    },
    {
      "dataset": "Humanity's Last Exam: Output Tokens per Task",
      "rank": 19,
      "total": 20,
      "value": 841.3021316033364
    },
    {
      "dataset": "AA-Omniscience Index: Cost Breakdown",
      "rank": 19,
      "total": 20,
      "value": 5.12813
    },
    {
      "dataset": "Time per Task",
      "rank": 20,
      "total": 20,
      "value": 40.85280634401213
    }
  ]
}