HELM MMLU - High School Government And Politics: leaderboard
Metric: EM. Source: crfm.stanford.edu. 79 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 1.5 Pro (002) | 98.96 |
| 2 | Qwen 2.5 72B Instruct | 98.96 |
| 3 | GPT-4 (0613) | 98.96 |
| 4 | Qwen 1.5 72B | 98.96 |
| 5 | Llama 3.3 70B Instruct | 98.45 |
| 6 | Claude 3.5 Sonnet (20241022) | 98.45 |
| 7 | Llama 3.1 70B Instruct | 98.45 |
| 8 | GPT-4o (2024-08-06) | 98.45 |
| 9 | Llama 3.1 405B Instruct | 98.45 |
| 10 | Qwen 1.5 110B | 98.45 |
| 11 | Claude 3.5 Sonnet (20240620) | 97.93 |
| 12 | Llama 3.2 90B Vision Instruct | 97.93 |
| 13 | DeepSeek V3 | 97.93 |
| 14 | GPT-4o (2024-05-13) | 97.93 |
| 15 | Gemma 2 27B | 97.93 |
Interactive version: theaggregate.ai/benchmark?slug=helm-mmlu-high-school-government-and-politics · How It Works · Data refreshed daily, snapshot 2026-09-08.