language benchmark
BoolQ
BoolQ is a reading comprehension dataset for yes/no questions containing 15,942 naturally occurring examples. Each example consists of a question, passage, and boolean answer, where questions are generated in unprompted and unconstrained settings. The dataset challenges models with complex, non-factoid information requiring entailment-like inference to solve.
Updated Aug 11, 2026
Models10
Model coverage10
MetricScore
EvidenceB
BoolQ Ranking
Higher score ranks better on this benchmark.
| 1 | NR | 88.0% | 100.0% | 10 | C | |
| 2 | GO | 84.8% | 88.9% | 10 | C | |
| 3 | MI | 84.6% | 77.8% | 10 | C | |
| 4 | GO | 84.2% | 66.7% | 10 | C | |
| 5 | GO | 81.6% | 55.6% | 10 | C | |
| 6 | GO | 81.6% | 44.4% | 10 | C | |
| 7 | MI | 81.2% | 33.3% | 10 | C | |
| 8 | MI | 78.0% | 22.2% | 10 | C | |
| 9 | GO | 76.4% | 11.1% | 10 | C | |
| 10 | GO | 76.4% | 0.0% | 10 | C |
BoolQ Score Distribution
A closer view of the leading scores on this benchmark.
BoolQ Highlights
The leading models and scores on this benchmark.
What is BoolQ?
What BoolQ measures and how its scores work.
BoolQ is a reading comprehension dataset for yes/no questions containing 15,942 naturally occurring examples. Each example consists of a question, passage, and boolean answer, where questions are generated in unprompted and unconstrained settings. The dataset challenges models with complex, non-factoid information requiring entailment-like inference to solve.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- BoolQ
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- boolq|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about BoolQ.
Which model scores highest on BoolQ?
Hermes 3 70B is currently ranked first with 88.0%.
What does BoolQ measure?
BoolQ is a reading comprehension dataset for yes/no questions containing 15,942 naturally occurring examples. Each example consists of a question, passage, and boolean answer, where questions are generated in unprompted and unconstrained settings. The dataset challenges models with complex, non-factoid information requiring entailment-like inference to solve.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
10 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.