HELM Classic - QuAC — leaderboard
Metric: F1 (%). Source: crfm.stanford.edu. 66 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | text-davinci-003 | 52.48 |
| 2 | GPT-3.5 Turbo (0301) | 51.2 |
| 3 | GPT-3.5 Turbo (0613) | 48.5 |
| 4 | Llama 2 70B | 48.44 |
| 5 | text-davinci-002 | 44.51 |
| 6 | Llama 2 13B | 42.38 |
| 7 | Mistral-7B-v0.1 | 42.32 |
| 8 | Llama 2 7B | 40.62 |
| 9 | LLaMA-65B | 40.13 |
| 10 | mpt-30B | 39.31 |
| 11 | LLaMA-30B | 39.02 |
| 12 | davinci | 36.04 |
| 13 | text-curie-001 | 35.79 |
| 14 | LLaMA-13B | 34.75 |
| 15 | LLaMA-7B | 33.76 |
Interactive version: theaggregate.ai/benchmark?slug=helm-classic-quac · How the rankings work · Data refreshed daily, snapshot 2026-07-22.