DDeepSeek R1: healthcare benchmark results
DeepSeek · 3 boards · snapshot reviewed September 28, 2026
The index currently holds 3 results for DeepSeek R1: 0.485 on MedHELM (7 of 10 indexed rows), 55.8% on First, Do NOHARM (v2) (17 of 17 indexed rows), 52.9% on WHBench [DeepSeek-R1] (10 of 22 indexed rows). Scores below sit on different scales and come from different graders, so read each against its own benchmark, never against the others.
Results by benchmark
| benchmark | score | index position | as of |
|---|---|---|---|
| MedHELM | 0.485 | 7 of 10 source board: 11 | 2026-05 |
| First, Do NOHARM (v2) | 55.8% | 17 of 17 source board: 19 | 2026-08 |
| WHBench DeepSeek-R1 95% bootstrap CI 50.5–55.3; 3 runs; temperature 0; zero-shot, closed-book via paper, arxiv.org | 52.9% | 10 of 22 | 2026-03 |
Position follows the rows held in this index and is not a controlled comparison. Sources may use different graders or task subsets. Positions include separate configurations. A source board may contain additional rows; its size is listed separately when it differs. Config caveats, where a source noted any, are on each benchmark's page, and the document behind each score is cited on the sources page. Sources also list this model as "DeepSeek-R1".
Which healthcare benchmarks is DeepSeek R1 scored on?
As of September 28, 2026, DeepSeek R1 has indexed results on 3 tracked benchmarks: MedHELM, First, Do NOHARM (v2), WHBench.
Which results are indexed for DeepSeek R1?
DeepSeek R1 stands at 0.485 on MedHELM (7 of 10 indexed rows), 55.8% on First, Do NOHARM (v2) (17 of 17 indexed rows), 52.9% on WHBench [DeepSeek-R1] (10 of 22 indexed rows).
The benchmarks themselves are described on their pages, linked in the table above, and the whole field is on the index.