Clinical Benchmarks

Google

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

Models
22
Results
58
Boards
13 of 14

deepmind.google

Models

ModelKindReleasedBoards
Gemini 4 ArgonModel30 Sep 20266
Gemini 3.8 FlashModel2 Sep 20267
Gemini 3.7 FlashModel13 Aug 20262
Gemini 3.5 Flash LiteModel21 Jul 20262
Gemini 3.6 FlashModel21 Jul 20263
Gemma 4 12BModel3 Jun 20261
Gemini 3.5 FlashModel19 May 20262
Gemma 4 26B A4BModel2 Apr 20261
Gemma 4 31BModel2 Apr 20261
Gemma 4 E2BModel2 Apr 20261
Gemma 4 E4BModel2 Apr 20261
Gemini 3.1 Flash Lite PreviewModel3 Mar 20262
Gemini 3.1 ProModel19 Feb 20266
Gemini 3 FlashModel17 Dec 20253
Gemini 3 ProModel18 Nov 20252
Gemini 2.5 Flash Lite (9/25)Model25 Sep 20251
Gemini 2.5 Flash Preview (9/25)Model25 Sep 20251
Gemini 2.5 Flash LiteModel22 Jul 20252
Gemini 2.5 FlashModel17 Jun 20251
Gemini 2.5 ProModel17 Jun 20253
Gemini 2.5 Flash (7/17)ModelNot stated1
Gemini 3 Pro (11/25)ModelNot stated1

Results

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

Clinical reasoning and knowledge

  1. HealthBench Professional
    Artificial Analysis independent run, high reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (64.2 raw, 5,133 mean response chars)
    0.551
    Rank 25 of 43Leader GPT-6 Astra (Anthropic run) 0.703
    Independent run
    Measured Oct 2026
  2. HealthBench Professional
    Artificial Analysis independent run, high reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (59.0 raw, 4,494 mean response chars)
    0.517
    Rank 32 of 43Leader GPT-6 Astra (Anthropic run) 0.703
    Independent run
    Measured Oct 2026
  3. MedXpertQA (MM)
    Meta's Muse Spark launch table (Meta reports the better of vendor self-reports and its own reproduction)
    81.3
    Rank 2 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
    Independent run
    Measured Apr 2026
  4. MedXpertQA (MM)
    Qwen3.5 model card comparison; source-specific evaluation, not harmonized across vendors
    76.0
    Rank 7 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
    Independent run
    Measured Feb 2026
  5. MedXpertQA (MM)
    Google model card; MedXPertQA MM row; vendor-reported; protocol differs from other source families
    61.3
    Rank 17 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
    Vendor-reported
    Measured Apr 2026
  6. MedXpertQA (MM)
    Google model card; MedXPertQA MM row; vendor-reported; protocol differs from other source families
    58.1
    Rank 18 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
    Vendor-reported
    Measured Apr 2026
  7. MedXpertQA (MM)
    Google's Gemma 4 model card, Unified 12B; protocol not stated
    48.7
    Rank 19 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
    Vendor-reported
    Measured Apr 2026
  8. MedXpertQA (MM)
    Google model card; MedXPertQA MM row; vendor-reported; protocol differs from other source families
    28.7
    Rank 21 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
    Vendor-reported
    Measured Apr 2026
  9. MedXpertQA (MM)
    Google model card; MedXPertQA MM row; vendor-reported; protocol differs from other source families
    23.5
    Rank 22 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
    Vendor-reported
    Measured Apr 2026
  10. 59.3
    Rank 3 of 8 here, 11 models on the boardLeader GPT-5.6 Sol 60.2
    Official leaderboard
    Measured Aug 2026
  11. 58.9
    Rank 4 of 8 here, 11 models on the boardLeader GPT-5.6 Sol 60.2
    Official leaderboard
    Measured Aug 2026
  12. 92.7
    Rank 4 of 15 here, 16 models on the boardLeader Claude Opus 5 94.6
    Official leaderboard
    Measured Oct 2026
  13. 86.5
    Rank 11 of 15 here, 16 models on the boardLeader Claude Opus 5 94.6
    Official leaderboard
    Measured Oct 2026
  14. APEX-1 GP
    Score (avg@4), reasoning high
    68.36
    Rank 3 of 12Leader Claude Opus 5.5 73.04
    Official leaderboard
    Measured Oct 2026

Documentation and coding

  1. 87.43
    Rank 15 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Oct 2026
  2. MedScribe (Vals AI)
    model ID google/gemini-3.8-flash; temperature=1; max_output_tokens=65536; reasoning_effort=high
    84.50
    Rank 33 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 google/gemini-3.7-flash; temperature=1; max_output_tokens=30000; reasoning_effort=high
    83.94
    Rank 38 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 google/gemini-2.5-flash-thinking; temperature=1; max_output_tokens=30000
    82.98
    Rank 46 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 google/gemini-2.5-flash; temperature=1; max_output_tokens=30000
    82.87
    Rank 48 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 google/gemini-3.6-flash; temperature=1; max_output_tokens=30000; reasoning_effort=high
    79.66
    Rank 59 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 google/gemini-2.5-flash-preview-09-2025-thinking; temperature=1; max_output_tokens=30000
    78.50
    Rank 62 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  8. MedScribe (Vals AI)
    model ID google/gemini-2.5-flash-preview-09-2025; temperature=1; max_output_tokens=30000
    77.95
    Rank 65 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  9. MedScribe (Vals AI)
    model ID google/gemini-3.5-flash; temperature=1; max_output_tokens=30000; reasoning_effort=high
    76.57
    Rank 72 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  10. MedScribe (Vals AI)
    model ID google/gemini-3.1-pro-preview; temperature=1; max_output_tokens=30000; reasoning_effort=high
    76.11
    Rank 74 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  11. MedScribe (Vals AI)
    model ID google/gemini-2.5-flash-lite-preview-09-2025; temperature=1; max_output_tokens=30000
    75.82
    Rank 76 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  12. MedScribe (Vals AI)
    model ID google/gemini-2.5-pro; temperature=1; max_output_tokens=30000
    73.55
    Rank 81 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  13. MedScribe (Vals AI)
    model ID google/gemini-2.5-flash-lite; temperature=1; max_output_tokens=30000
    72.83
    Rank 83 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  14. MedScribe (Vals AI)
    model ID google/gemini-3-pro-preview; temperature=1; max_output_tokens=30000; reasoning_effort=high
    72.04
    Rank 88 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  15. MedScribe (Vals AI)
    model ID google/gemini-3.5-flash-lite; temperature=1; max_output_tokens=30000; reasoning_effort=high
    70.89
    Rank 90 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  16. MedScribe (Vals AI)
    model ID google/gemini-3-flash-preview; temperature=1; max_output_tokens=30000; reasoning_effort=high
    69.92
    Rank 92 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  17. MedScribe (Vals AI)
    model ID google/gemini-2.5-flash-lite-preview-09-2025-thinking; temperature=1; max_output_tokens=30000
    66.88
    Rank 97 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  18. MedScribe (Vals AI)
    model ID google/gemini-3.1-flash-lite-preview; temperature=1; max_output_tokens=30000; reasoning_effort=high
    63.90
    Rank 99 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  19. 59.06
    Rank 2 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  20. 58.80
    Rank 3 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Oct 2026
  21. 55.92
    Rank 5 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  22. 55.83
    Rank 6 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  23. MedCode (Vals AI)
    model ID google/gemini-3.7-flash; reasoning_effort=high; temperature=1; max_output_tokens=30000
    53.39
    Rank 9 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  24. 53.15
    Rank 11 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  25. MedCode (Vals AI)
    model ID google/gemini-3-pro-preview; reasoning_effort=high; temperature=1; max_output_tokens=30000
    52.20
    Rank 14 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  26. MedCode (Vals AI)
    model ID google/gemini-2.5-pro; temperature=1; max_output_tokens=30000
    50.59
    Rank 16 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  27. MedCode (Vals AI)
    model ID google/gemini-3.8-flash; reasoning_effort=high; temperature=1; max_output_tokens=65536
    48.13
    Rank 29 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  28. MedCode (Vals AI)
    model ID google/gemini-3.1-flash-lite-preview; reasoning_effort=high; temperature=1; max_output_tokens=30000
    47.60
    Rank 30 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  29. MedCode (Vals AI)
    model ID google/gemini-3.5-flash-lite; reasoning_effort=high; temperature=1; max_output_tokens=30000
    43.49
    Rank 42 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  30. MedCode (Vals AI)
    model ID google/gemini-2.5-flash-preview-09-2025; temperature=1; max_output_tokens=30000
    40.54
    Rank 61 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  31. MedCode (Vals AI)
    model ID google/gemini-2.5-flash-thinking; temperature=1; max_output_tokens=30000
    40.36
    Rank 63 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  32. MedCode (Vals AI)
    model ID google/gemini-2.5-flash-preview-09-2025-thinking; temperature=1; max_output_tokens=30000
    40.33
    Rank 64 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  33. MedCode (Vals AI)
    model ID google/gemini-2.5-flash; temperature=1; max_output_tokens=30000
    38.42
    Rank 69 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  34. MedCode (Vals AI)
    model ID google/gemini-2.5-flash-lite-preview-09-2025-thinking; temperature=1; max_output_tokens=30000
    34.19
    Rank 78 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  35. MedCode (Vals AI)
    model ID google/gemini-2.5-flash-lite; temperature=1; max_output_tokens=30000
    27.11
    Rank 99 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  36. MedCode (Vals AI)
    model ID google/gemini-2.5-flash-lite-preview-09-2025; temperature=1; max_output_tokens=30000
    27.08
    Rank 100 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  37. MLCR-AA
    overall pass rate, High
    10.6
    Rank 25 of 27Leader Claude Sonnet 5.5 (Max, Default Fallback) 41.7
    Independent run
    Measured Nov 2026

EHR and workflow agents

  1. 6.0
    Rank 26 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; gemini-cli harness
    12.5
    Rank 28 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
    Official leaderboard
    Measured Apr 2026
  3. RCM-Bench
    Score (avg@3), medium reasoning
    91.49
    Rank 2 of 20Leader Claude Opus 5 92.68
    Official leaderboard
    Measured Oct 2026
  4. RCM-Bench
    Score (avg@3), medium reasoning
    90.23
    Rank 6 of 20Leader Claude Opus 5 92.68
    Official leaderboard
    Measured Oct 2026
  5. DAYJOB Health
    Score (pass@1 at 95%), reasoning high
    23.6
    Rank 8 of 15Leader Claude Opus 5.5 48.3
    Official leaderboard
    Measured Oct 2026

Safety

  1. 62.6
    Rank 12 of 17 here, 19 models on the boardLeader LiSA 2.5 86.2
    Official leaderboard
    Measured Aug 2026
  2. 61.9
    Rank 13 of 17 here, 19 models on the boardLeader LiSA 2.5 86.2
    Official leaderboard
    Measured Aug 2026