Clinical Benchmarks
Menu

MAST (Medical AI Superintelligence Test)

A composite of clinical benchmarks spanning diagnostic and management reasoning, safety, multimodal imaging, and agentic capability.

ARISE AI Research Network8 rows8 of 11 models on the boardmeasured to Aug 2026

Official page
More about this boardLess

A composite of clinical benchmarks spanning diagnostic and management reasoning, safety, multimodal imaging, and agentic capability.

Composite score across curated clinical benchmarks spanning diagnostic reasoning, management reasoning, safety, multimodal images, multimodal radiology, and agentic capability. Components: First Do NOHARM v2, SCT-Bench, MedAgentBench v2, PhysicianBench, ReXrank Mini, CPC-Bench.

The board is marked as a preview and was last updated August 15, 2026; component-level breakdowns are published only for First, Do NOHARM v2. Scores may move before the full release.

Published by ARISE AI Research Network (multi-institutional), released Aug 2026. Composite of 6 component benchmarks; 11 models. Percentage composite, higher better.

Board marked as preview
Yes
How the composite is formed
harmonic mean of Diagnostic Reasoning, Management Reasoning, Safety, Multimodal Radiology, Multimodal Images
Board last updated
15 Aug 2026
Rows the board shows by default
latest large and small model from each provider
Board generated
2026-08-15 18:28 UTC
Models in the board's default view
11

Preview: MAST is currently in preview. Exact scores on this benchmark may change as we undergo final validation and tuning.

Ranking

  1. 1GPT-5.6 SolOpenAI · MAST in preview60.2
    Printed as 60.2%Official leaderboard, measured Aug 2026Configuration: MAST in preview; 'exact scores may change'
    MAST: Medical AI Superintelligence Test leaderboard (General board) official leaderboard, ARISE AI Research Network, 15 Aug 2026. arise-ai.org/mast, 'Which AI can you trust for medical questions?' General tab, composite score table (8 of 11 models shown; 'Last updated August 15, 2026')
    1 GPT-5.6 Sol OpenAI 60.2%
    Every result from this document

    Link to this row

  2. 2Kimi K3Moonshot AI60.1
    Printed as 60.1%Official leaderboard, measured Aug 2026
    MAST: Medical AI Superintelligence Test leaderboard (General board) official leaderboard, ARISE AI Research Network, 15 Aug 2026. arise-ai.org/mast, 'Which AI can you trust for medical questions?' General tab, composite score table (8 of 11 models shown; 'Last updated August 15, 2026')
    2 Kimi K3 Moonshot AI 60.1%
    Every result from this document

    Link to this row

  3. 3Gemini 3.6 FlashGoogle59.3
    Printed as 59.3%Official leaderboard, measured Aug 2026
    MAST: Medical AI Superintelligence Test leaderboard (General board) official leaderboard, ARISE AI Research Network, 15 Aug 2026. arise-ai.org/mast, 'Which AI can you trust for medical questions?' General tab, composite score table (8 of 11 models shown; 'Last updated August 15, 2026')
    3 Gemini 3.6 Flash Google 59.3%
    Every result from this document

    Link to this row

  4. 4Gemini 3.1 ProGoogle58.9
    Printed as 58.9%Official leaderboard, measured Aug 2026
    MAST: Medical AI Superintelligence Test leaderboard (General board) official leaderboard, ARISE AI Research Network, 15 Aug 2026. arise-ai.org/mast, 'Which AI can you trust for medical questions?' General tab, composite score table (8 of 11 models shown; 'Last updated August 15, 2026')
    4 Gemini 3.1 Pro Google 58.9%
    Every result from this document

    Link to this row

  5. 5Qwen3.5 397B A17BAlibaba57.9
    Printed as 57.9%Official leaderboard, measured Aug 2026
    MAST: Medical AI Superintelligence Test leaderboard (General board) official leaderboard, ARISE AI Research Network, 15 Aug 2026. arise-ai.org/mast, 'Which AI can you trust for medical questions?' General tab, composite score table (8 of 11 models shown; 'Last updated August 15, 2026')
    5 Qwen3.5 397B A17B Alibaba 57.9%
    Every result from this document

    Link to this row

  6. 6Claude Opus 5Anthropic57.1
    Printed as 57.1%Official leaderboard, measured Aug 2026
    MAST: Medical AI Superintelligence Test leaderboard (General board) official leaderboard, ARISE AI Research Network, 15 Aug 2026. arise-ai.org/mast, 'Which AI can you trust for medical questions?' General tab, composite score table (8 of 11 models shown; 'Last updated August 15, 2026')
    6 Claude Opus 5 Anthropic 57.1%
    Every result from this document

    Link to this row

  7. 7Claude Sonnet 5Anthropic56.6
    Printed as 56.6%Official leaderboard, measured Aug 2026
    MAST: Medical AI Superintelligence Test leaderboard (General board) official leaderboard, ARISE AI Research Network, 15 Aug 2026. arise-ai.org/mast, 'Which AI can you trust for medical questions?' General tab, composite score table (8 of 11 models shown; 'Last updated August 15, 2026')
    7 Claude Sonnet 5 Anthropic 56.6%
    Every result from this document

    Link to this row

  8. 8Grok 4.3SpaceX AI53.7
    Printed as 53.7%Official leaderboard, measured Aug 2026
    MAST: Medical AI Superintelligence Test leaderboard (General board) official leaderboard, ARISE AI Research Network, 15 Aug 2026. arise-ai.org/mast, 'Which AI can you trust for medical questions?' General tab, composite score table (8 of 11 models shown; 'Last updated August 15, 2026')
    8 Grok 4.3 xAI 53.7%
    Every result from this document

    Link to this row

Percentage composite, higher better. Bar colour: the lab; a pale bar with an outline is a number the model’s own lab reported. Select a row for its quote, page and document.

Documents

1 document supports this board