MMLU-by-task - Anatomy — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 1257 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | falcon-180B | 65.19 |
| 2 | Llama 2 70B Base | 62.96 |
| 3 | Mistral-7B-v0.1 | 62.96 |
| 4 | StableBeluga2 | 62.96 |
| 5 | Llama 2 70B Chat | 60 |
| 6 | LLaMA-65B | 57.78 |
| 7 | falcon-40B Instruct | 54.07 |
| 8 | internlm-20B Chat | 54.07 |
| 9 | MythoMax-L2-13B | 52.59 |
| 10 | Llama 2 70B Chat (HF) | 51.85 |
| 11 | trurl-2-13B-academic | 51.85 |
| 12 | LLaMA-30B | 51.11 |
| 13 | WizardLM-13B-V1.2 | 51.11 |
| 14 | Llama 2 70B Chat GPTQ | 51.11 |
| 15 | vicuna-7B-v1.5 | 50.37 |
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-anatomy · How the rankings work · Data refreshed daily, snapshot 2026-07-22.