MMLU-by-task - Astronomy — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 1257 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 2 70B Base | 80.92 |
| 2 | Llama 2 70B Chat | 79.61 |
| 3 | StableBeluga2 | 78.95 |
| 4 | falcon-180B | 78.95 |
| 5 | Llama 2 70B Chat (HF) | 73.03 |
| 6 | Llama 2 70B Chat GPTQ | 73.03 |
| 7 | LLaMA-65B | 71.71 |
| 8 | Mistral-7B-v0.1 | 65.79 |
| 9 | vicuna-33B-v1.3 | 65.13 |
| 10 | LLaMA-30B | 61.18 |
| 11 | internlm-20B Chat | 57.89 |
| 12 | OpenHermes-13B | 57.24 |
| 13 | trurl-2-13B-academic | 56.58 |
| 14 | vicuna-13B-v1.5 | 55.92 |
| 15 | falcon-40B Instruct | 55.26 |
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-astronomy · How the rankings work · Data refreshed daily, snapshot 2026-07-22.