HELM Classic - BoolQ: leaderboard
The "BoolQ" subtask of HELM Classic. A scenario from Stanford HELM Classic, the holistic evaluation suite scoring language models across accuracy, robustness and calibration on a broad set of tasks.
Metric: Exact Match (%). Source: crfm.stanford.edu. Saturation forecast: Estimated already saturated. 67 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Palmyra X (43B) | 89.63 | #1317 |
| 2 | Llama 2 70B | 88.6 | #1201 |
| 3 | text-davinci-003 | 88.13 | #1146 |
| 4 | text-davinci-002 | 87.7 | #1225 |
| 5 | Mistral-7B-v0.1 | 87.4 | #1326 |
| 6 | LLaMA-65B | 87.1 | #1303 |
| 7 | GPT-3.5 Turbo (0613) | 87 | #1118 |
| 8 | LLaMA-30B | 86.1 | #1423 |
| 9 | mpt-30B Instruct | 85 | #1470 |
| 10 | falcon-40B Instruct | 82.9 | #1458 |
| 11 | falcon-40B | 81.9 | #1442 |
| 12 | Llama 2 13B | 81.1 | #1436 |
| 13 | vicuna-13B-v1.3 | 80.8 | #1447 |
| 14 | OPT-175B | 79.3 | #1538 |
| 15 | GLM-130B | 78.37 | #1568 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=helm-classic-boolq · How It Works · Data refreshed daily, snapshot 2026-10-20.