MMLU-by-task - High School Computer Science — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 1257 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 2 70B Base | 79 |
| 2 | Llama 2 70B Chat | 77 |
| 3 | StableBeluga2 | 75 |
| 4 | falcon-180B | 73 |
| 5 | Mistral-7B-v0.1 | 68 |
| 6 | LLaMA-65B | 68 |
| 7 | internlm-20B Chat | 66 |
| 8 | Llama 2 70B Chat (HF) | 65 |
| 9 | Llama 2 70B Chat GPTQ | 65 |
| 10 | vicuna-33B-v1.3 | 63 |
| 11 | WizardCoder-Python-34B-V1.0 | 62 |
| 12 | LLaMA-30B | 60 |
| 13 | WizardLM-13B-V1.2 | 60 |
| 14 | Llama 2 13B Chat Base | 59 |
| 15 | MythoMax-L2-13B | 56 |
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-high-school-computer-science · How the rankings work · Data refreshed daily, snapshot 2026-07-22.