language benchmark
BoolQ Leaderboard
BoolQ is a reading comprehension dataset of 15,942 naturally occurring yes/no questions with passages and boolean answers.
Updated Sep 5, 2026
Models10
Model coverage10
MetricScore
EvidenceB
BoolQ Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelNR | Score88.04% | Percentile100.00% | Participants10 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score84.80% | Percentile88.89% | Participants10 | EvidenceC | Evaluated |
| Rank03 | ModelMI | Score84.60% | Percentile77.78% | Participants10 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score84.20% | Percentile66.67% | Participants10 | EvidenceC | Evaluated |
| Rank05 | ModelGO | Score81.60% | Percentile55.56% | Participants10 | EvidenceC | Evaluated |
| Rank06 | ModelGO | Score81.60% | Percentile44.44% | Participants10 | EvidenceC | Evaluated |
| Rank07 | ModelMI | Score81.20% | Percentile33.33% | Participants10 | EvidenceC | Evaluated |
| Rank08 | ModelMI | Score78.00% | Percentile22.22% | Participants10 | EvidenceC | Evaluated |
| Rank09 | ModelGO | Score76.40% | Percentile11.11% | Participants10 | EvidenceC | Evaluated |
| Rank10 | ModelGO | Score76.40% | Percentile0.00% | Participants10 | EvidenceC | Evaluated |
BoolQ Highlights
The leading models and scores on this benchmark.
BoolQ Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for BoolQ
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is BoolQ?
What BoolQ measures and how its scores work.
BoolQ is a language benchmark based on questions, passages, and boolean answers, including questions generated in unprompted and unconstrained settings.
It measures performance on yes/no reading comprehension questions involving entailment-like inference, reported as Score in ratio units.
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
- No
- Evaluation key
- overall
LLM Stats. 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 88.04%.
What are the top three models on BoolQ?
The current leaders are Hermes 3 70B (88.04%), Gemma 2 27B (84.80%), and Phi-3.5-MoE-instruct (84.60%).
Which BoolQ model has the lowest official input price?
Phi 4 Mini has the lowest matched official input price at $0.08 input / $0.30 output per 1M tokens.
Which models are fastest among BoolQ results?
The fastest matched records are Phi-3.5-mini-instruct (23.00 tok/s via Azure).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.