HELM AFR - MMLU Clinical Knowledge (Tsonga): leaderboard
Metric: EM. Source: crfm.stanford.edu. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.0 Flash | 70.19 |
| 2 | Claude 3.7 Sonnet (20250219) | 65.28 |
| 3 | GPT-4o (2024-08-06) | 64.15 |
| 4 | DeepSeek V3 | 61.13 |
| 5 | Gemini 2.0 Flash Lite | 61.13 |
| 6 | GPT-4 Turbo | 55.47 |
| 7 | Llama 3.1 405B Instruct | 54.34 |
| 8 | Llama 3.1 70B Instruct | 51.32 |
| 9 | Llama 3.3 70B Instruct | 48.3 |
| 10 | Gemma 2 27B (IT) | 43.77 |
| 11 | Qwen 2.5 72B Instruct | 42.64 |
| 12 | Claude 3.5 Haiku (20241022) | 42.26 |
| 13 | Llama 3.1 8B Instruct | 38.87 |
| 14 | GPT-3.5 Turbo (0125) | 35.85 |
| 15 | Gemma 2 9B (IT) | 34.72 |
Interactive version: theaggregate.ai/benchmark?slug=helm-afr-mmlu-clinical-knowledge-tsonga · How It Works · Data refreshed daily, snapshot 2026-09-08.