MMLU-by-task - High School Mathematics — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 1257 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | falcon-180B | 38.89 |
| 2 | Llama 2 70B Base | 35.56 |
| 3 | WizardCoder-Python-34B-V1.0 | 34.44 |
| 4 | LLaMA-65B | 34.07 |
| 5 | Mistral-7B-v0.1 | 33.7 |
| 6 | falcon-40B Instruct | 33.33 |
| 7 | StableBeluga2 | 32.96 |
| 8 | mpt-30B Instruct | 32.96 |
| 9 | MythoMax-L2-13B | 32.59 |
| 10 | WizardLM-13B-V1.2 | 32.22 |
| 11 | trurl-2-13B-academic | 32.22 |
| 12 | vicuna-13B-v1.5 | 31.85 |
| 13 | Llama 2 13B Chat Base | 31.11 |
| 14 | CodeLlama-34B-Instruct-hf | 31.11 |
| 15 | OpenHermes-13B | 30.74 |
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-high-school-mathematics · How the rankings work · Data refreshed daily, snapshot 2026-07-22.