reasoning 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 7, 2026
Published models10
Registry coverage10
MetricScore
EvidenceB
BoolQ leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 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 |
Score distribution
Top published rows on the benchmark's original scale.
BoolQ highlights
The top published results on this benchmark's own scale.
What is BoolQ?
Definition and scoring fields from the benchmark registry.
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. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- BoolQ
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- boolq|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is marked as eligible for the current LLMBoard capability methodology.