OpenEval - BoolQ: leaderboard
Human-Centered Eval OpenEval run of BoolQ exact match, testing yes/no reading comprehension over naturally occurring questions.
Metric: Exact Match (%). Source: huggingface.co. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | pythia-6.9B | 70.31 | #1646 |
Interactive version: theaggregate.ai/benchmark?slug=openeval-boolq · How It Works · Data refreshed daily, snapshot 2026-10-20.