HELM MMLU - High School Psychology: leaderboard
The "High School Psychology" 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) | 96.7 | #293 |
| 2 | Gemini 1.5 Pro (002) | 96.7 | #352 |
| 3 | Claude 3.5 Sonnet (20240620) | 95.96 | #300 |
| 4 | DeepSeek V3 | 95.96 | #325 |
| 5 | GPT-4o (2024-05-13) | 95.6 | #328 |
| 6 | GPT-4o (2024-08-06) | 95.41 | #337 |
| 7 | GPT-4 Turbo (Preview) | 95.41 | #404 |
| 8 | Llama 3.3 70B Instruct | 95.23 | #537 |
| 9 | Qwen 2.5 72B Instruct | 95.05 | #463 |
| 10 | GPT-4 Turbo | 95.05 | #410 |
| 11 | Nova Pro | 95.05 | #574 |
| 12 | Llama 3.1 70B Instruct | 94.86 | #567 |
| 13 | Llama 3.1 405B Instruct | 94.86 | #464 |
| 14 | Llama 3.2 90B Vision Instruct | 94.86 | #625 |
| 15 | GPT-4 (0613) | 94.86 | #496 |
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-psychology · How It Works · Data refreshed daily, snapshot 2026-10-24.