Clinical Benchmarks
Menu

DeepSeek R1

Released 20 Jan 2025128K context671B total / 37B activemit

2 results on 2 of 13 boards, latest measured Aug 2026. Compare with other models

Clinical Benchmarks Index29.5Rank 58 of 1492 of 10 boardsAverage × multiplier 51.2 × 0.577 = 29.5This site’s own calculation. Working How it is computed

Results

Each line sits on its own board's scale. Tall tick: the board leader.

Clinical reasoning and knowledge

  1. MedHELM
    0.485
    Rank 7 of 10 here, 11 models on the boardLeader Gemini 3.1 Pro (Preview) 0.652
    Official leaderboard
    Measured May 2026

Safety

  1. First, Do NOHARM (v2)
    55.8
    Rank 17 of 17 here, 19 models on the boardLeader LiSA 2.5 86.2
    Official leaderboard
    Measured Aug 2026

Index working

The Clinical Benchmarks Index is this site's own calculation: a weighted average of the board scores times a multiplier for the boards behind it. How it is computed

  • MedHELM0.48548.5×0.87
  • First, Do NOHARM (v2)55.855.8×0.507
Weighted average of 2 boards
51.2
Multiplier for 2 of 10 boards
× 0.577
Index
51.2 × 0.577 = 29.5

Score: the result on the board’s own 0 to 100 scale. Dot: this model; tick: the board’s leader. Weight: how much the board counts in the weighted average. Each result links to its quote and page; the line under it is the setting it was measured with.

Sources

The quote, page and document for each of the 2 results
  1. 7MedHELM 0.485
    Printed as 0.485Official leaderboard, measured May 2026
    MedHELM leaderboard (medhelm.org), v5.0.0 official leaderboard, Stanford CRFM (MedHELM), 14 May 2026. medhelm.org home, 'Current leaders Mean win rate v5.0.0' table ('10 of 11 models · Updated 14 May 2026')
    7 DeepSeek R1 DeepSeek 0.485
    Every result from this document
  2. 17First, Do NOHARM (v2) 55.8
    Printed as 55.8%Official leaderboard, measured Aug 2026
    MAST technical leaderboard (First Do NOHARM v2 and per-benchmark results) official leaderboard, ARISE AI Research Network, 15 Aug 2026. arise-ai.org/mast/technical, 'First Do NOHARM v2 overall metric across 19 models' ranking (Latest Flagships view)
    16DeepSeek R1OSSDeepSeek 55.8%
    Every result from this document

Other DeepSeek models: DeepSeek-V3.1, DeepSeek-V3.2-Exp, DeepSeek V4.1 Flash, DeepSeek V4 Flash, DeepSeek V4 Flash 0731, DeepSeek V4 Pro