Clinical Benchmarks

MiniMax

MiniMax models with results here, each shown on its own board.

Models
3
Results
7
Boards
3 of 13

www.minimax.io

Models

ModelKindReleasedBoards
MiniMax M3Model1 Jun 20262
MiniMax-M2.7Model18 Mar 20263
MiniMax-M2.1ModelNot stated2

Results

One line per result. Tall tick: the board leader.

Documentation and coding

  1. 87.25
    Rank 15 of 105Leader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  2. MedScribe (Vals AI)
    model ID minimax/MiniMax-M2.1; temperature=1; top_p=0.95; max_output_tokens=30000
    80.78
    Rank 52 of 105Leader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  3. MedScribe (Vals AI)
    model ID minimax/MiniMax-M2.7; temperature=1; top_p=0.95; max_output_tokens=30000
    79.87
    Rank 56 of 105Leader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  4. MedCode (Vals AI)
    model ID minimax/MiniMax-M3; temperature=1; top_p=0.95; max_output_tokens=30000
    46.29
    Rank 34 of 103Leader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  5. MedCode (Vals AI)
    model ID minimax/MiniMax-M2.7; temperature=1; top_p=0.95; max_output_tokens=30000
    34.44
    Rank 76 of 103Leader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  6. MedCode (Vals AI)
    model ID minimax/MiniMax-M2.1; temperature=1; top_p=0.95; max_output_tokens=30000
    34.08
    Rank 78 of 103Leader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026

EHR and workflow agents

  1. PhysicianBench
    Pass@1 over 3 runs; Pass^3 1.0; shared FHIR tool harness; up to 100 turns; high reasoning when supported
    8.7
    Rank 25 of 28 here, 12 models on the boardLeader Claude Opus 5.5 (max) 68.4
    Official leaderboard
    Measured May 2026