HELM Classic - RAFT — leaderboard
Metric: Exact Match (%). Source: crfm.stanford.edu. 67 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-3.5 Turbo (0301) | 76.82 |
| 2 | text-davinci-003 | 75.91 |
| 3 | LLaMA-30B | 75.23 |
| 4 | GPT-3.5 Turbo (0613) | 74.77 |
| 5 | text-davinci-002 | 73.26 |
| 6 | Llama 2 70B | 72.73 |
| 7 | mpt-30B | 72.27 |
| 8 | Mistral-7B-v0.1 | 70.68 |
| 9 | Llama 2 13B | 70.68 |
| 10 | LLaMA-65B | 70.23 |
| 11 | falcon-40B | 66.14 |
| 12 | LLaMA-13B | 64.32 |
| 13 | Llama 2 7B | 64.32 |
| 14 | davinci | 64.24 |
| 15 | gpt-j-6B | 61.89 |
Interactive version: theaggregate.ai/benchmark?slug=helm-classic-raft · How the rankings work · Data refreshed daily, snapshot 2026-07-22.