HELM MMLU - International Law: leaderboard
The "International Law" 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) | 95.87 | #291 |
| 2 | Claude 3.5 Sonnet (20240620) | 95.87 | #298 |
| 3 | DeepSeek V3 | 95.04 | #323 |
| 4 | Llama 3.1 405B Instruct | 95.04 | #461 |
| 5 | GPT-4o (2024-08-06) | 94.21 | #335 |
| 6 | GPT-4 Turbo | 94.21 | #406 |
| 7 | GPT-4o (2024-05-13) | 93.39 | #326 |
| 8 | Llama 3.2 90B Vision Instruct | 93.39 | #626 |
| 9 | Llama 3.1 70B Instruct | 92.56 | #566 |
| 10 | GPT-4o Mini (2024-07-18) | 92.56 | #561 |
| 11 | Mistral Large 2 (Jul) | 92.56 | #485 |
| 12 | GPT-4 Turbo (Preview) | 92.56 | #399 |
| 13 | Gemini 1.5 Pro (002) | 91.74 | #350 |
| 14 | GPT-4 (0613) | 91.74 | #494 |
| 15 | Gemini 1.5 Pro (001) | 91.74 | #446 |
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-international-law · How It Works · Data refreshed daily, snapshot 2026-10-23.