HELM MMLU - Clinical Knowledge: leaderboard
The "Clinical Knowledge" subtask of HELM MMLU. HELM Classic MMLU group leaderboard from the public HELM release artifacts.
Metric: EM. Source: crfm.stanford.edu. Saturation forecast: Estimated already saturated. 79 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.5 Sonnet (20241022) | 92.83 | #293 |
| 2 | Claude 3.5 Sonnet (20240620) | 91.32 | #300 |
| 3 | DeepSeek V3 | 91.32 | #325 |
| 4 | Gemini 1.5 Pro (002) | 90.57 | #352 |
| 5 | GPT-4o (2024-08-06) | 89.43 | #337 |
| 6 | GPT-4o (2024-05-13) | 89.43 | #328 |
| 7 | Llama 3.1 405B Instruct | 87.92 | #464 |
| 8 | Gemini 2.0 Flash (Preview) | 87.92 | #369 |
| 9 | Claude 3 Opus (20240229) | 87.92 | #420 |
| 10 | Nova Pro | 87.55 | #574 |
| 11 | Qwen 2.5 72B Instruct | 87.17 | #463 |
| 12 | Qwen 2 72B Instruct | 86.79 | #581 |
| 13 | Mistral Large 2 (Jul) | 86.42 | #489 |
| 14 | GPT-4 Turbo (Preview) | 86.42 | #404 |
| 15 | Gemini 1.5 Pro (001) | 85.28 | #461 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=helm-mmlu-clinical-knowledge · How It Works · Data refreshed daily, snapshot 2026-10-24.