MMLU-by-task - Computer Security — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 1257 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | falcon-180B | 80 |
| 2 | LLaMA-65B | 79 |
| 3 | Llama 2 70B Base | 77 |
| 4 | Mistral-7B-v0.1 | 77 |
| 5 | Llama 2 70B Chat | 75 |
| 6 | StableBeluga2 | 75 |
| 7 | Llama 2 70B Chat (HF) | 71 |
| 8 | WizardCoder-Python-34B-V1.0 | 70 |
| 9 | MythoMax-L2-13B | 69 |
| 10 | vicuna-33B-v1.3 | 69 |
| 11 | Llama 2 13B Chat Base | 68 |
| 12 | OpenHermes-13B | 68 |
| 13 | internlm-20B Chat | 68 |
| 14 | trurl-2-13B-academic | 68 |
| 15 | vicuna-13B-v1.3 | 67 |
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-computer-security · How the rankings work · Data refreshed daily, snapshot 2026-07-22.