MMLU-by-task - Machine Learning: leaderboard
The "Machine Learning" 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 | 59.82 | #1237 |
| 2 | Llama 2 70B Base | 53.57 | #1025 |
| 3 | Xwin-LM-70B-V0.1 | 50 | #982 |
| 4 | WizardLM-70B-V1.0 | 49.11 | #1236 |
| 5 | internlm-20B | 49.11 | #1296 |
| 6 | Mistral-7B-v0.1 | 48.21 | #1326 |
| 7 | Llama 2 70B Chat (HF) | 48.21 | #1264 |
| 8 | vicuna-33B-v1.3 | 46.43 | #1347 |
| 9 | StableBeluga2 | 46.43 | #1078 |
| 10 | mpt-30B | 45.54 | #1476 |
| 11 | vicuna-13B-v1.5 | 44.64 | #1392 |
| 12 | vicuna-13B-v1.3 | 43.75 | #1447 |
| 13 | ChatGLM2 6B | 43.75 | #1498 |
| 14 | Baichuan-7B | 41.96 | #1527 |
| 15 | Vicuna-7B-v1.5-16k | 39.29 | #1491 |
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-machine-learning · How It Works · Data refreshed daily, snapshot 2026-10-20.