HELM MMLU - Moral Disputes: leaderboard
The "Moral Disputes" 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 (20240620) | 88.73 | #300 |
| 2 | GPT-4o (2024-05-13) | 88.15 | #328 |
| 3 | Claude 3 Opus (20240229) | 88.15 | #420 |
| 4 | DeepSeek V3 | 87.28 | #325 |
| 5 | Claude 3.5 Sonnet (20241022) | 86.99 | #293 |
| 6 | GPT-4o (2024-08-06) | 86.99 | #337 |
| 7 | Llama 3.1 405B Instruct | 86.99 | #464 |
| 8 | GPT-4 (0613) | 86.71 | #496 |
| 9 | Gemini 2.0 Flash (Preview) | 86.42 | #369 |
| 10 | GPT-4 Turbo | 86.13 | #410 |
| 11 | GPT-4 Turbo (Preview) | 85.84 | #404 |
| 12 | Gemini 1.5 Pro (002) | 85.55 | #352 |
| 13 | Llama 3.3 70B Instruct | 85.26 | #537 |
| 14 | Qwen 2 72B Instruct | 85.26 | #581 |
| 15 | Llama 3.2 90B Vision Instruct | 84.97 | #625 |
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-moral-disputes · How It Works · Data refreshed daily, snapshot 2026-10-24.