HELM MMLU - Nutrition: leaderboard
The "Nutrition" 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 | Llama 3.1 405B Instruct | 92.81 | #461 |
| 2 | Claude 3 Opus (20240229) | 92.48 | #413 |
| 3 | Claude 3.5 Sonnet (20241022) | 92.16 | #291 |
| 4 | DeepSeek V3 | 91.83 | #323 |
| 5 | Claude 3.5 Sonnet (20240620) | 91.18 | #298 |
| 6 | GPT-4o (2024-08-06) | 90.52 | #335 |
| 7 | Qwen 2 72B Instruct | 90.2 | #579 |
| 8 | GPT-4o (2024-05-13) | 89.87 | #326 |
| 9 | GPT-4 Turbo | 89.22 | #406 |
| 10 | GPT-4 (0613) | 89.22 | #494 |
| 11 | Llama 3.1 70B Instruct | 88.89 | #566 |
| 12 | Llama 3.2 90B Vision Instruct | 88.89 | #626 |
| 13 | Qwen 2.5 72B Instruct | 88.56 | #458 |
| 14 | Gemini 1.5 Pro (002) | 88.56 | #350 |
| 15 | Llama 3.3 70B Instruct | 88.24 | #536 |
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-nutrition · How It Works · Data refreshed daily, snapshot 2026-10-23.