HELM MMLU - Jurisprudence: leaderboard
The "Jurisprudence" 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 | GPT-4o (2024-08-06) | 90.74 | #337 |
| 2 | Claude 3.5 Sonnet (20241022) | 89.81 | #293 |
| 3 | Gemini 1.5 Pro (002) | 89.81 | #352 |
| 4 | DeepSeek V3 | 89.81 | #325 |
| 5 | GPT-4o (2024-05-13) | 89.81 | #328 |
| 6 | Gemini 2.0 Flash (Preview) | 89.81 | #369 |
| 7 | Yi 34B (Base) | 89.81 | #973 |
| 8 | Llama 3.1 70B Instruct | 88.89 | #567 |
| 9 | Claude 3.5 Sonnet (20240620) | 88.89 | #300 |
| 10 | GPT-4 (0613) | 88.89 | #496 |
| 11 | Gemini 1.5 Pro (001) | 88.89 | #461 |
| 12 | Gemini 1.5 Flash (001) | 88.89 | #587 |
| 13 | GPT-4 Turbo (Preview) | 88.89 | #404 |
| 14 | GPT-4 Turbo | 87.96 | #410 |
| 15 | Claude 3 Opus (20240229) | 87.96 | #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-jurisprudence · How It Works · Data refreshed daily, snapshot 2026-10-24.