Clinical Benchmarks

DDeepSeek: healthcare benchmark results

1 model · 2 results · updated September 8, 2026

Everything the index holds for DeepSeek, gathered in one place: DeepSeek R1. Scores sit on each benchmark's own scale and never compare across rows from different boards.

Every result

modelbenchmarkscoreindex position
DeepSeek R1MedHELM0.4857 of 10
source board: 11
DeepSeek R1First, Do NOHARM (v2)55.8%12 of 12
source board: 19

Positions refer to indexed rows, including configuration variants. Source board sizes appear separately where coverage differs.

Which healthcare benchmarks does DeepSeek appear on?

As of September 8, 2026, DeepSeek models hold 2 current results across 2 tracked benchmarks, through DeepSeek R1.

Where does DeepSeek lead?

DeepSeek holds no first places on the tracked boards right now.

Other labs with pages: OpenAI, Anthropic, Google, Moonshot AI, Meta, Alibaba, xAI, MiniMax, Microsoft, Thinking Machines, Mistral. The full field is on the index.