MMLU-by-task - Management: leaderboard
The "Management" subtask of MMLU-by-task. A single MMLU subject, reporting per-task multiple-choice accuracy from the MMLU-by-task leaderboard across a wide range of academic and professional domains.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 1257 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 2 70B Chat | 84.47 | #1237 |
| 2 | Llama 2 70B Base | 83.5 | #1025 |
| 3 | StableBeluga2 | 82.52 | #1078 |
| 4 | Mistral-7B-v0.1 | 81.55 | #1326 |
| 5 | WizardLM-70B-V1.0 | 81.55 | #1236 |
| 6 | Xwin-LM-70B-V0.1 | 81.55 | #982 |
| 7 | Llama 2 70B Chat (HF) | 80.58 | #1264 |
| 8 | vicuna-33B-v1.3 | 77.67 | #1347 |
| 9 | internlm-20B | 77.67 | #1296 |
| 10 | falcon-40B Instruct | 75.73 | #1458 |
| 11 | Llama 2 13B Chat Base | 73.79 | #1422 |
| 12 | vicuna-13B-v1.5 | 72.82 | #1392 |
| 13 | trurl-2-13B-academic | 71.84 | #1413 |
| 14 | Nous-Hermes-13B | 71.84 | #1468 |
| 15 | vicuna-13B-v1.3 | 70.87 | #1447 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-management · How It Works · Data refreshed daily, snapshot 2026-10-20.