{
  "url": "https://www.aibattle.space/models/mistral-medium-3-5",
  "slug": "mistral-medium-3-5",
  "name": "Mistral Medium 3.5",
  "creator": "Mistral",
  "rebuilt": "2026-09-19",
  "placements": [
    {
      "dataset": "GDPval-AA v2: Output Tokens per Task",
      "rank": 2,
      "total": 20,
      "value": 17551.2
    },
    {
      "dataset": "Output Tokens per Intelligence Index Task",
      "rank": 3,
      "total": 20,
      "value": 12065.772317071056
    },
    {
      "dataset": "Output Tokens per Intelligence Index Task",
      "rank": 3,
      "total": 20,
      "value": 12065.772317071056
    },
    {
      "dataset": "AA-Briefcase Output Tokens per Task",
      "rank": 3,
      "total": 20,
      "value": 32096.53846153846
    },
    {
      "dataset": "Time per Task",
      "rank": 3,
      "total": 20,
      "value": 4.671876712933692
    },
    {
      "dataset": "Terminal-Bench v4.0: Time per Task",
      "rank": 4,
      "total": 20,
      "value": 7.1481168226241545
    },
    {
      "dataset": "Time per Intelligence Index Task",
      "rank": 5,
      "total": 20,
      "value": 2.7695621772006493
    },
    {
      "dataset": "Latency: Time To First Answer Token",
      "rank": 5,
      "total": 20,
      "value": 2.248213874
    },
    {
      "dataset": "Time per Intelligence Index Task",
      "rank": 5,
      "total": 20,
      "value": 2.7695621772006493
    },
    {
      "dataset": "End-to-End Response Time",
      "rank": 6,
      "total": 20,
      "value": 2.248213874
    },
    {
      "dataset": "AA-Briefcase Cost per Task",
      "rank": 6,
      "total": 20,
      "value": 0.24072403846153845
    },
    {
      "dataset": "Cost per Intelligence Index Task",
      "rank": 7,
      "total": 20,
      "value": 0.01620853681211329
    },
    {
      "dataset": "Output Speed",
      "rank": 7,
      "total": 20,
      "value": 146.949591761798
    },
    {
      "dataset": "Cost per Intelligence Index Task",
      "rank": 7,
      "total": 20,
      "value": 0.01620853681211329
    },
    {
      "dataset": "Output Speed",
      "rank": 7,
      "total": 20,
      "value": 146.949591761798
    },
    {
      "dataset": "Terminal-Bench v4.0: Cost per Task",
      "rank": 7,
      "total": 20,
      "value": 0
    },
    {
      "dataset": "𝜏³-Banking: Time per Task",
      "rank": 7,
      "total": 20,
      "value": 1.1162907120254064
    },
    {
      "dataset": "Terminal-Bench v4.0: Output Tokens per Task",
      "rank": 8,
      "total": 20,
      "value": 38059.28787878788
    },
    {
      "dataset": "GDPval-AA v2: Cost per Task",
      "rank": 8,
      "total": 20,
      "value": 0
    },
    {
      "dataset": "Cost to Run Artificial Analysis Intelligence Index",
      "rank": 11,
      "total": 20,
      "value": 131.60504999999998
    },
    {
      "dataset": "Cost to Run Artificial Analysis Intelligence Index",
      "rank": 11,
      "total": 20,
      "value": 131.60504999999998
    },
    {
      "dataset": "MMMU-Pro: Token Usage",
      "rank": 11,
      "total": 19,
      "value": 330058
    },
    {
      "dataset": "Humanity's Last Exam: Time per Task",
      "rank": 12,
      "total": 20,
      "value": 2.8567257469328857
    },
    {
      "dataset": "AA-Omniscience Index: Token Usage",
      "rank": 13,
      "total": 20,
      "value": 708722
    },
    {
      "dataset": "MMMU-Pro: Total Cost to Run",
      "rank": 13,
      "total": 19,
      "value": 0.49508700000000005
    },
    {
      "dataset": "AA-Omniscience Index: Cost Breakdown",
      "rank": 14,
      "total": 20,
      "value": 1.063083
    },
    {
      "dataset": "𝜏³-Banking: Cost per Task",
      "rank": 14,
      "total": 20,
      "value": 0
    },
    {
      "dataset": "Model Size: Total and Active Parameters",
      "rank": 11,
      "total": 14,
      "value": 128
    },
    {
      "dataset": "Humanity's Last Exam: Cost per Task",
      "rank": 16,
      "total": 20,
      "value": 0.00046383225208526414
    },
    {
      "dataset": "AA-LCR v1.1: Cost per Task",
      "rank": 16,
      "total": 20,
      "value": 0.14149457999999998
    },
    {
      "dataset": "AA-AnalystAgent pass^5",
      "rank": 9,
      "total": 11,
      "value": 0.125
    },
    {
      "dataset": "Pricing: Cache Hit, Input, and Output",
      "rank": 17,
      "total": 20,
      "value": 1.5
    },
    {
      "dataset": "Pricing: Cache Hit, Input, and Output",
      "rank": 17,
      "total": 20,
      "value": 1.5
    },
    {
      "dataset": "AA-LCR v1.1: Time per Task",
      "rank": 17,
      "total": 20,
      "value": 0.41792838104050806
    },
    {
      "dataset": "𝜏³-Banking: Output Tokens per Task",
      "rank": 17,
      "total": 20,
      "value": 2299.855670103093
    },
    {
      "dataset": "SciCode: Time per Task",
      "rank": 17,
      "total": 20,
      "value": 1.1173579084196168
    },
    {
      "dataset": "Artificial Analysis Openness Index: Score",
      "rank": 11,
      "total": 12,
      "value": 33.333333333333336
    },
    {
      "dataset": "Artificial Analysis Openness Index: Components",
      "rank": 11,
      "total": 12,
      "value": 5
    },
    {
      "dataset": "Humanity's Last Exam: Output Tokens per Task",
      "rank": 20,
      "total": 20,
      "value": 331.33734939759034
    },
    {
      "dataset": "MMMU-Pro: Score",
      "rank": 19,
      "total": 19,
      "value": 0.648554913294798
    },
    {
      "dataset": "SciCode: Cost per Task",
      "rank": 20,
      "total": 20,
      "value": 0.002735395833333333
    }
  ]
}