HELM MMLU - Machine Learning: leaderboard
The "Machine Learning" 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) | 83.93 | #291 |
| 2 | Gemini 1.5 Pro (002) | 83.04 | #350 |
| 3 | Llama 3.1 405B Instruct | 79.46 | #461 |
| 4 | Claude 3.5 Sonnet (20240620) | 78.57 | #298 |
| 5 | DeepSeek V3 | 78.57 | #323 |
| 6 | Qwen 2.5 72B Instruct | 77.68 | #458 |
| 7 | GPT-4o (2024-08-06) | 77.68 | #335 |
| 8 | GPT-4o (2024-05-13) | 76.79 | #326 |
| 9 | Qwen 2 72B Instruct | 76.79 | #579 |
| 10 | Gemini 2.0 Flash (Preview) | 75.89 | #366 |
| 11 | GPT-4 (0613) | 75.89 | #494 |
| 12 | GPT-4 Turbo | 74.11 | #406 |
| 13 | Claude 3 Opus (20240229) | 74.11 | #413 |
| 14 | GPT-4 Turbo (Preview) | 72.32 | #399 |
| 15 | Llama 3.3 70B Instruct | 71.43 | #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-machine-learning · How It Works · Data refreshed daily, snapshot 2026-10-23.