HELM MMLU - High School Government And Politics: leaderboard
The "High School Government And Politics" 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 | Qwen 2.5 72B Instruct | 98.96 | #463 |
| 2 | Gemini 1.5 Pro (002) | 98.96 | #352 |
| 3 | GPT-4 (0613) | 98.96 | #496 |
| 4 | Qwen 1.5 72B | 98.96 | #759 |
| 5 | Llama 3.3 70B Instruct | 98.45 | #537 |
| 6 | Llama 3.1 70B Instruct | 98.45 | #567 |
| 7 | Claude 3.5 Sonnet (20241022) | 98.45 | #293 |
| 8 | GPT-4o (2024-08-06) | 98.45 | #337 |
| 9 | Llama 3.1 405B Instruct | 98.45 | #464 |
| 10 | Qwen 1.5 110B | 98.45 | #741 |
| 11 | Claude 3.5 Sonnet (20240620) | 97.93 | #300 |
| 12 | DeepSeek V3 | 97.93 | #325 |
| 13 | GPT-4o (2024-05-13) | 97.93 | #328 |
| 14 | Qwen 2 72B Instruct | 97.93 | #581 |
| 15 | Claude 3 Opus (20240229) | 97.93 | #420 |
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-government-and-politics · How It Works · Data refreshed daily, snapshot 2026-10-24.