HELM Classic - MMLU — leaderboard
Metric: Exact Match (%). Source: crfm.stanford.edu. 67 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-3.5 Turbo (0301) | 58.98 |
| 2 | LLaMA-65B | 58.37 |
| 3 | Llama 2 70B | 58.17 |
| 4 | Mistral-7B-v0.1 | 57.22 |
| 5 | text-davinci-003 | 56.88 |
| 6 | text-davinci-002 | 56.76 |
| 7 | LLaMA-30B | 53.14 |
| 8 | falcon-40B | 50.89 |
| 9 | Llama 2 13B | 50.67 |
| 10 | mpt-30B | 43.67 |
| 11 | Llama 2 7B | 43.07 |
| 12 | davinci | 42.24 |
| 13 | LLaMA-13B | 42.21 |
| 14 | GPT-3.5 Turbo (0613) | 39.09 |
| 15 | alpaca-7B | 38.46 |
Interactive version: theaggregate.ai/benchmark?slug=helm-classic-mmlu · How the rankings work · Data refreshed daily, snapshot 2026-07-22.