HELM MMLU - Management: leaderboard
The "Management" 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) | 94.17 | #300 |
| 2 | GPT-4o (2024-05-13) | 94.17 | #328 |
| 3 | Claude 3 Opus (20240229) | 94.17 | #420 |
| 4 | Claude 3.5 Sonnet (20241022) | 93.2 | #293 |
| 5 | GPT-4 (0613) | 93.2 | #496 |
| 6 | Claude 3 Sonnet (20240229) | 92.23 | #686 |
| 7 | Gemini 1.5 Pro (001) | 92.23 | #461 |
| 8 | Nova Pro | 92.23 | #574 |
| 9 | Llama 3.1 70B Instruct | 91.26 | #567 |
| 10 | Qwen 2.5 72B Instruct | 91.26 | #463 |
| 11 | GPT-4o (2024-08-06) | 91.26 | #337 |
| 12 | Llama 3.2 90B Vision Instruct | 91.26 | #625 |
| 13 | Llama 3 70B | 91.26 | #635 |
| 14 | GPT-4 Turbo (Preview) | 91.26 | #404 |
| 15 | Llama 3.3 70B Instruct | 90.29 | #537 |
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-management · How It Works · Data refreshed daily, snapshot 2026-10-24.