{
  "url": "https://www.aibattle.space/models/gpt-5-6-sol",
  "slug": "gpt-5-6-sol",
  "name": "GPT-5.6 Sol (max)",
  "creator": "OpenAI",
  "rebuilt": "2026-09-19",
  "placements": [
    {
      "dataset": "SciCode: Output Tokens per Task",
      "rank": 3,
      "total": 20,
      "value": 380.9826388888889
    },
    {
      "dataset": "𝜏³-Banking: Output Tokens per Task",
      "rank": 4,
      "total": 20,
      "value": 2405.1546391752577
    },
    {
      "dataset": "AA-LCR v1.1: Output Tokens per Task",
      "rank": 5,
      "total": 20,
      "value": 74.87
    },
    {
      "dataset": "Artificial Analysis Intelligence Index by Open Weights / Proprietary",
      "rank": 6,
      "total": 20,
      "value": 47.0613568915036
    },
    {
      "dataset": "Artificial Analysis Intelligence Index by Open Weights / Proprietary",
      "rank": 6,
      "total": 20,
      "value": 47.0613568915036
    },
    {
      "dataset": "Artificial Analysis Intelligence Index",
      "rank": 6,
      "total": 20,
      "value": 47.0613568915036
    },
    {
      "dataset": "Artificial Analysis Intelligence Index",
      "rank": 6,
      "total": 20,
      "value": 47.0613568915036
    },
    {
      "dataset": "AA-Briefcase Output Tokens per Task",
      "rank": 6,
      "total": 20,
      "value": 34731.34065934066
    },
    {
      "dataset": "AA-LCR v1.1: Score",
      "rank": 6,
      "total": 20,
      "value": 0.84
    },
    {
      "dataset": "MMMU-Pro: Token Usage",
      "rank": 6,
      "total": 19,
      "value": 999093
    },
    {
      "dataset": "Output Tokens per Intelligence Index Task",
      "rank": 7,
      "total": 20,
      "value": 12028.929221184391
    },
    {
      "dataset": "Artificial Analysis Finance & Accounting Index",
      "rank": 7,
      "total": 20,
      "value": 49.195616009069006
    },
    {
      "dataset": "Output Tokens per Intelligence Index Task",
      "rank": 7,
      "total": 20,
      "value": 12028.929221184391
    },
    {
      "dataset": "Humanity's Last Exam: Output Tokens per Task",
      "rank": 7,
      "total": 20,
      "value": 217.71640407784986
    },
    {
      "dataset": "AA-Omniscience Index",
      "rank": 8,
      "total": 20,
      "value": 21.9666666666667
    },
    {
      "dataset": "AA-Omniscience Index",
      "rank": 8,
      "total": 20,
      "value": 21.9666666666667
    },
    {
      "dataset": "AA-Briefcase Elo",
      "rank": 9,
      "total": 20,
      "value": 1475
    },
    {
      "dataset": "AA-Briefcase Elo",
      "rank": 9,
      "total": 20,
      "value": 1475
    },
    {
      "dataset": "AA-AnalystAgent pass^5",
      "rank": 5,
      "total": 11,
      "value": 0.475
    },
    {
      "dataset": "MMMU-Pro: Score",
      "rank": 9,
      "total": 19,
      "value": 0.834104046242775
    },
    {
      "dataset": "GDPval-AA v2 Leaderboard",
      "rank": 10,
      "total": 20,
      "value": 1624.11
    },
    {
      "dataset": "Humanity's Last Exam: Score",
      "rank": 10,
      "total": 20,
      "value": 0.494902687673772
    },
    {
      "dataset": "Terminal-Bench v4.0: Output Tokens per Task",
      "rank": 10,
      "total": 20,
      "value": 37484.545454545456
    },
    {
      "dataset": "AA-Omniscience Accuracy",
      "rank": 10,
      "total": 20,
      "value": 0.594
    },
    {
      "dataset": "GDPval-AA v2: Output Tokens per Task",
      "rank": 10,
      "total": 20,
      "value": 22677.1
    },
    {
      "dataset": "Terminal-Bench v4.0: Score",
      "rank": 11,
      "total": 20,
      "value": 0.398989898989899
    },
    {
      "dataset": "Time per Task",
      "rank": 11,
      "total": 20,
      "value": 20.256458748337636
    },
    {
      "dataset": "SciCode: Score",
      "rank": 11,
      "total": 20,
      "value": 0.570601851851852
    },
    {
      "dataset": "AA-Omniscience Index: Score",
      "rank": 13,
      "total": 20,
      "value": 21.9666666666667
    },
    {
      "dataset": "SciCode: Time per Task",
      "rank": 13,
      "total": 20,
      "value": 0.9537582230593853
    },
    {
      "dataset": "Time per Intelligence Index Task",
      "rank": 14,
      "total": 20,
      "value": 7.955351836618607
    },
    {
      "dataset": "Time per Intelligence Index Task",
      "rank": 14,
      "total": 20,
      "value": 7.955351836618607
    },
    {
      "dataset": "AA-Briefcase Elo",
      "rank": 14,
      "total": 20,
      "value": 1475
    },
    {
      "dataset": "AA-LCR v1.1: Time per Task",
      "rank": 14,
      "total": 20,
      "value": 0.32953393956303917
    },
    {
      "dataset": "GDPval-AA v2: Average Turns per Task",
      "rank": 14,
      "total": 20,
      "value": 45.2054794520548
    },
    {
      "dataset": "Terminal-Bench v4.0: Time per Task",
      "rank": 15,
      "total": 20,
      "value": 20.882070299008504
    },
    {
      "dataset": "GDPval-AA v2 Leaderboard",
      "rank": 15,
      "total": 20,
      "value": 1624.11
    },
    {
      "dataset": "𝜏³-Banking: Score",
      "rank": 15,
      "total": 20,
      "value": 0.443298969072165
    },
    {
      "dataset": "MMMU-Pro: Total Cost to Run",
      "rank": 15,
      "total": 19,
      "value": 3.996372
    },
    {
      "dataset": "Context Window",
      "rank": 16,
      "total": 20,
      "value": 1000000
    },
    {
      "dataset": "AA-Briefcase Cost per Task",
      "rank": 16,
      "total": 20,
      "value": 0.6946268131868132
    },
    {
      "dataset": "Cost per Intelligence Index Task",
      "rank": 17,
      "total": 20,
      "value": 0.08606791137271577
    },
    {
      "dataset": "Output Speed",
      "rank": 17,
      "total": 20,
      "value": 61.3538173198384
    },
    {
      "dataset": "Cost per Intelligence Index Task",
      "rank": 17,
      "total": 20,
      "value": 0.08606791137271577
    },
    {
      "dataset": "Output Speed",
      "rank": 17,
      "total": 20,
      "value": 61.3538173198384
    },
    {
      "dataset": "Humanity's Last Exam: Time per Task",
      "rank": 17,
      "total": 20,
      "value": 3.620110530602794
    },
    {
      "dataset": "Cost to Run Artificial Analysis Intelligence Index",
      "rank": 19,
      "total": 20,
      "value": 347.55454
    },
    {
      "dataset": "Cost to Run Artificial Analysis Intelligence Index",
      "rank": 19,
      "total": 20,
      "value": 347.55454
    },
    {
      "dataset": "𝜏³-Banking: Time per Task",
      "rank": 19,
      "total": 20,
      "value": 2.3276337526191293
    },
    {
      "dataset": "SciCode: Cost per Task",
      "rank": 19,
      "total": 20,
      "value": 0.009419486111111111
    },
    {
      "dataset": "End-to-End Response Time",
      "rank": 20,
      "total": 20,
      "value": 111.7845921055
    },
    {
      "dataset": "Pricing: Cache Hit, Input, and Output",
      "rank": 20,
      "total": 20,
      "value": 4
    },
    {
      "dataset": "Latency: Time To First Answer Token",
      "rank": 20,
      "total": 20,
      "value": 111.7845921055
    },
    {
      "dataset": "Pricing: Cache Hit, Input, and Output",
      "rank": 20,
      "total": 20,
      "value": 4
    },
    {
      "dataset": "AA-Briefcase Tool Calls Breakdown, Avg per Task",
      "rank": 20,
      "total": 20,
      "value": 40.62637362637363
    },
    {
      "dataset": "AA-Briefcase Rubric Pass Rate by File Type (Normalized)",
      "rank": 20,
      "total": 20,
      "value": 0.5512820512820512
    }
  ]
}