MMLU-by-task - Elementary Mathematics — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 1257 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | falcon-180B | 48.94 |
| 2 | Llama 2 70B Chat | 45.5 |
| 3 | StableBeluga2 | 43.92 |
| 4 | Llama 2 70B Base | 43.39 |
| 5 | Llama 2 70B Chat (HF) | 41.01 |
| 6 | WizardCoder-Python-34B-V1.0 | 41.01 |
| 7 | LLaMA-65B | 40.48 |
| 8 | Llama 2 70B Chat GPTQ | 39.95 |
| 9 | internlm-20B Chat | 37.83 |
| 10 | vicuna-33B-v1.3 | 37.57 |
| 11 | Mistral-7B-v0.1 | 37.3 |
| 12 | LLaMA-30B | 37.3 |
| 13 | OpenHermes-13B | 35.98 |
| 14 | trurl-2-13B-academic | 35.45 |
| 15 | Llama 2 13B Chat Base | 34.13 |
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-elementary-mathematics · How the rankings work · Data refreshed daily, snapshot 2026-07-22.