reasoning benchmark
Natural Questions Leaderboard
Natural Questions is a question-answering dataset of real anonymized queries issued to Google search engine, with 307,373 training examples annotated with long answers, short answers, or unanswerable labels from Wikipedia pages.
Updated Sep 5, 2026
Models7
Model coverage7
MetricScore
EvidenceB
Natural Questions Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score34.50% | Percentile100.00% | Participants7 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score31.20% | Percentile83.33% | Participants7 | EvidenceC | Evaluated |
| Rank03 | ModelGO | Score29.20% | Percentile66.67% | Participants7 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score20.90% | Percentile50.00% | Participants7 | EvidenceC | Evaluated |
| Rank05 | ModelGO | Score20.90% | Percentile33.33% | Participants7 | EvidenceC | Evaluated |
| Rank06 | ModelGO | Score15.50% | Percentile16.67% | Participants7 | EvidenceC | Evaluated |
| Rank07 | ModelGO | Score15.50% | Percentile0.00% | Participants7 | EvidenceC | Evaluated |
Natural Questions Highlights
The leading models and scores on this benchmark.
Natural Questions Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Natural Questions
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Natural Questions?
What Natural Questions measures and how its scores work.
Natural Questions is a question-answering dataset featuring real anonymized queries issued to Google search engine and annotations from Wikipedia pages.
It reports a Score measured as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Natural Questions
- Modality
- text
- Primary category
- reasoning
- 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 Natural Questions.
Which model scores highest on Natural Questions?
Gemma 2 27B is currently ranked first with 34.50%.
What are the top three models on Natural Questions?
The current leaders are Gemma 2 27B (34.50%), Mistral NeMo Instruct (31.20%), and Gemma 2 9B (29.20%).
Which Natural Questions model has the lowest official input price?
Mistral NeMo Instruct has the lowest matched official input price at $0.15 input / $0.15 output per 1M tokens.
Which models are fastest among Natural Questions results?
The fastest matched records are Mistral NeMo Instruct (42.00 tok/s via Google).
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.