Clinical Benchmarks

Alibaba

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

Models
12
Results
28
Boards
8 of 14

qwen.ai

Models

ModelKindReleasedBoards
Qwen3.8 MaxModel3 Aug 20264
Qwen3.7 PlusModel31 May 20261
Qwen3.6 PlusModel1 Apr 20264
Qwen3.5 397B A17BModel16 Feb 20263
Qwen 3 Max ThinkingModelNot stated2
Qwen 3 VL PlusModelNot stated2
Qwen 3.5 FlashModelNot stated2
Qwen 3.7 MaxModelNot stated2
Qwen 3.8 27BModelNot stated2
Qwen3-VL-235B-A22BModelNot stated1
Qwen3.6-MaxModelNot stated1
Qwen3.8 27BModelNot stated1

Results

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

Clinical reasoning and knowledge

  1. MedXpertQA (MM)
    Alibaba's own Qwen3.8 launch table; protocol not stated
    80.4
    Rank 3 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
    Vendor-reported
    Measured Aug 2026
  2. MedXpertQA (MM)
    Alibaba's own Qwen3.7 Plus launch table; protocol not stated
    71.0
    Rank 10 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
    Vendor-reported
    Measured May 2026
  3. MedXpertQA (MM)
    self-reported in the Qwen3.5-397B-A17B model card
    70.0
    Rank 11 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
    Vendor-reported
  4. MedXpertQA (MM)
    Qwen-run comparison in the Qwen3.7-Plus launch post
    68.7
    Rank 12 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
    Vendor-reported
  5. MedXpertQA (MM)
    Qwen3.5 model card comparison; source-specific evaluation, not harmonized across vendors
    47.6
    Rank 20 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
    Vendor-reported
    Measured Feb 2026
  6. 57.9
    Rank 5 of 8 here, 11 models on the boardLeader GPT-5.6 Sol 60.2
    Official leaderboard
    Measured Aug 2026

Documentation and coding

  1. MedScribe (Vals AI)
    model ID alibaba/qwen3.8-max; temperature=1; max_output_tokens=30000
    84.95
    Rank 31 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  2. MedScribe (Vals AI)
    model ID alibaba/qwen3.8-27b; temperature=1; top_p=0.95; max_output_tokens=30000; reasoning_effort=xhigh
    83.85
    Rank 39 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  3. MedScribe (Vals AI)
    model ID alibaba/qwen3.7-max; temperature=1; max_output_tokens=30000
    79.40
    Rank 60 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  4. MedScribe (Vals AI)
    model ID alibaba/qwen3-vl-plus-2025-09-23; temperature=1; max_output_tokens=30000
    77.13
    Rank 68 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  5. MedScribe (Vals AI)
    model ID alibaba/qwen3.6-plus; temperature=1; max_output_tokens=30000
    76.96
    Rank 70 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  6. MedScribe (Vals AI)
    model ID alibaba/qwen3-max-2026-01-23; temperature=1; max_output_tokens=30000
    72.71
    Rank 84 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  7. MedScribe (Vals AI)
    model ID alibaba/qwen3.5-flash; temperature=1; max_output_tokens=30000
    70.62
    Rank 91 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  8. MedCode (Vals AI)
    model ID alibaba/qwen3.8-max; temperature=1; max_output_tokens=30000
    40.67
    Rank 59 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  9. MedCode (Vals AI)
    model ID alibaba/qwen3.7-max; temperature=1; max_output_tokens=30000
    38.75
    Rank 67 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  10. MedCode (Vals AI)
    model ID alibaba/qwen3.6-plus; temperature=1; max_output_tokens=30000
    36.89
    Rank 74 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  11. MedCode (Vals AI)
    model ID alibaba/qwen3.5-flash; temperature=1; max_output_tokens=30000
    33.00
    Rank 83 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  12. MedCode (Vals AI)
    model ID alibaba/qwen3-vl-plus-2025-09-23; temperature=1; max_output_tokens=30000
    31.65
    Rank 90 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  13. MedCode (Vals AI)
    model ID alibaba/qwen3-max-2026-01-23; temperature=1; max_output_tokens=30000
    31.37
    Rank 91 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  14. MedCode (Vals AI)
    model ID alibaba/qwen3.8-27b; reasoning_effort=xhigh; temperature=1; top_p=0.95; max_output_tokens=30000
    28.70
    Rank 96 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  15. MLCR-AA
    overall pass rate, Xhigh
    22.8
    Rank 12 of 27Leader Claude Sonnet 5.5 (Max, Default Fallback) 41.7
    Independent run
    Measured Nov 2026
  16. MLCR-AA
    overall pass rate, 0902
    20.0
    Rank 15 of 27Leader Claude Sonnet 5.5 (Max, Default Fallback) 41.7
    Independent run
    Measured Nov 2026

EHR and workflow agents

  1. 13.7
    Rank 24 of 28 here, 12 models on the boardLeader Claude Opus 5.5 (max) 68.4
    Official leaderboard
    Measured May 2026
  2. CHI-Bench
    All Domains pass@1; hermes harness; Qwen3.6-Max preview endpoint
    16.4
    Rank 19 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
    Official leaderboard
    Measured May 2026
  3. CHI-Bench
    All Domains pass@1; openai-agents harness; Qwen3.6-Max preview endpoint
    15.6
    Rank 21 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
    Official leaderboard
    Measured May 2026
  4. CHI-Bench
    All Domains pass@1; deepagents harness; Qwen3.6-Max preview endpoint
    9.3
    Rank 33 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
    Official leaderboard
    Measured May 2026
  5. CHI-Bench
    All Domains pass@1; openclaw harness; Qwen3.6-Max preview endpoint
    4.9
    Rank 38 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
    Official leaderboard
    Measured May 2026

Safety

  1. 61.1
    Rank 14 of 17 here, 19 models on the boardLeader LiSA 2.5 86.2
    Official leaderboard
    Measured Aug 2026