HELM Classic - BoolQ — leaderboard
Metric: Exact Match (%). Source: crfm.stanford.edu. 67 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 2 70B | 88.6 |
| 2 | text-davinci-003 | 88.13 |
| 3 | text-davinci-002 | 87.7 |
| 4 | Mistral-7B-v0.1 | 87.4 |
| 5 | LLaMA-65B | 87.1 |
| 6 | GPT-3.5 Turbo (0613) | 87 |
| 7 | LLaMA-30B | 86.1 |
| 8 | falcon-40B | 81.9 |
| 9 | Llama 2 13B | 81.1 |
| 10 | alpaca-7B | 77.8 |
| 11 | Llama 2 7B | 76.2 |
| 12 | LLaMA-7B | 75.6 |
| 13 | falcon-7B | 75.3 |
| 14 | GPT-3.5 Turbo (0301) | 74 |
| 15 | davinci | 72.23 |
Interactive version: theaggregate.ai/benchmark?slug=helm-classic-boolq · How the rankings work · Data refreshed daily, snapshot 2026-07-22.