MMLU-by-task - High School Psychology — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 1257 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | falcon-180B | 90.64 |
| 2 | Llama 2 70B Chat | 89.17 |
| 3 | StableBeluga2 | 88.81 |
| 4 | Llama 2 70B Base | 87.34 |
| 5 | Llama 2 70B Chat (HF) | 83.85 |
| 6 | Llama 2 70B Chat GPTQ | 83.67 |
| 7 | LLaMA-65B | 82.94 |
| 8 | Mistral-7B-v0.1 | 82.39 |
| 9 | internlm-20B Chat | 79.08 |
| 10 | vicuna-33B-v1.3 | 78.17 |
| 11 | LLaMA-30B | 76.33 |
| 12 | vicuna-13B-v1.5 | 75.6 |
| 13 | falcon-40B Instruct | 75.41 |
| 14 | trurl-2-13B-academic | 74.13 |
| 15 | OpenHermes-13B | 73.58 |
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-high-school-psychology · How the rankings work · Data refreshed daily, snapshot 2026-07-22.