SuperGLUE BoolQ: leaderboard
BoolQ (Clark et al., 2019), a SuperGLUE task: naturally occurring yes/no questions from Google search queries, each answered from a Wikipedia passage. Archived Papers With Code table of accuracies as each paper reported them, under that paper’s own setup; higher is better.
Metric: Accuracy. Source: huggingface.co. Saturation forecast: Rough model projection: around 2026. 65 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | OPT-175B | 60.1 | #1507 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superglue-boolq · How It Works · Data refreshed daily, snapshot 2026-11-05.