HELM MMLU - High School Mathematics: leaderboard
The "High School Mathematics" 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 | DeepSeek V3 | 76.67 | #325 |
| 2 | Gemini 1.5 Pro (002) | 72.96 | #352 |
| 3 | Gemini 1.5 Pro (001) | 68.52 | #461 |
| 4 | Qwen 2.5 72B Instruct | 66.3 | #463 |
| 5 | Llama 3.1 405B Instruct | 63.7 | #464 |
| 6 | Claude 3.5 Sonnet (20240620) | 63.33 | #300 |
| 7 | Claude 3.5 Sonnet (20241022) | 62.96 | #293 |
| 8 | Gemini 2.0 Flash (Preview) | 62.96 | #369 |
| 9 | Nova Pro | 61.48 | #574 |
| 10 | Qwen 2 72B Instruct | 59.63 | #581 |
| 11 | Claude 3 Opus (20240229) | 58.52 | #420 |
| 12 | Nova Lite | 58.15 | #758 |
| 13 | GPT-4 (0613) | 54.44 | #496 |
| 14 | Jamba 1.5 Large | 54.44 | #677 |
| 15 | GPT-4 Turbo | 51.48 | #410 |
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-high-school-mathematics · How It Works · Data refreshed daily, snapshot 2026-10-24.