HELM MMLU - Us Foreign Policy: leaderboard
The "Us Foreign Policy" 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 | 96 | #458 |
| 2 | Claude 3.5 Sonnet (20241022) | 96 | #291 |
| 3 | Claude 3.5 Sonnet (20240620) | 96 | #298 |
| 4 | GPT-4o (2024-05-13) | 96 | #326 |
| 5 | GPT-4 Turbo | 96 | #406 |
| 6 | Claude 3 Opus (20240229) | 96 | #413 |
| 7 | GPT-4 Turbo (Preview) | 96 | #399 |
| 8 | GPT-4o (2024-08-06) | 95 | #335 |
| 9 | Claude 3 Haiku (20240307) | 95 | #777 |
| 10 | GPT-4 (0613) | 95 | #494 |
| 11 | Gemma 2 27B | 95 | #812 |
| 12 | Mixtral 8x22B | 95 | #770 |
| 13 | Gemini 1.5 Pro (002) | 94 | #350 |
| 14 | Llama 3.1 405B Instruct | 94 | #461 |
| 15 | Qwen 2 72B Instruct | 94 | #579 |
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-us-foreign-policy · How It Works · Data refreshed daily, snapshot 2026-10-23.