HELM MMLU - International Law: leaderboard
Metric: EM. Source: crfm.stanford.edu. 79 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet (20241022) | 95.87 |
| 2 | Claude 3.5 Sonnet (20240620) | 95.87 |
| 3 | DeepSeek V3 | 95.04 |
| 4 | Llama 3.1 405B Instruct | 95.04 |
| 5 | GPT-4o (2024-08-06) | 94.21 |
| 6 | GPT-4 Turbo | 94.21 |
| 7 | Llama 3.2 90B Vision Instruct | 93.39 |
| 8 | GPT-4o (2024-05-13) | 93.39 |
| 9 | Llama 3.1 70B Instruct | 92.56 |
| 10 | GPT-4o Mini (2024-07-18) | 92.56 |
| 11 | Mistral Large 2 (Jul) | 92.56 |
| 12 | GPT-4 Turbo (Preview) | 92.56 |
| 13 | Gemini 1.5 Pro (002) | 91.74 |
| 14 | Gemini 1.5 Pro (001) | 91.74 |
| 15 | GPT-4 (0613) | 91.74 |
Interactive version: theaggregate.ai/benchmark?slug=helm-mmlu-international-law · How It Works · Data refreshed daily, snapshot 2026-09-08.