reasoning benchmark
Natural Questions Leaderboard
Natural Questions is a question answering dataset featuring real anonymized queries issued to Google search engine. It contains 307,373 training examples where annotators provide long answers (passages) and short answers (entities) from Wikipedia pages, or mark them as unanswerable.
Updated Aug 17, 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 | Score34.5% | Percentile100.0% | Participants7 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score31.2% | Percentile83.3% | Participants7 | EvidenceC | Evaluated |
| Rank03 | ModelGO | Score29.2% | Percentile66.7% | Participants7 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score20.9% | Percentile50.0% | Participants7 | EvidenceC | Evaluated |
| Rank05 | ModelGO | Score20.9% | Percentile33.3% | Participants7 | EvidenceC | Evaluated |
| Rank06 | ModelGO | Score15.5% | Percentile16.7% | Participants7 | EvidenceC | Evaluated |
| Rank07 | ModelGO | Score15.5% | Percentile0.0% | 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.
Ranking basisThis natural questions AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01GOGemma 2 27BGoogle
- Score
- 34.5%
Strengths
- Ranks #1 of 7 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures Natural Questions, not total model capability
- 02MAMistral NeMo InstructMistral AI
- Score
- 31.2%
- Price
- $0.15 input / $0.15 output per 1M tokens
- Speed
- Up to 42 tok/s via Google
Strengths
- Ranks #2 of 7 compared models
- 83th percentile on this benchmark
- C evidence result
Considerations
- This result measures Natural Questions, not total model capability
- 03GOGemma 2 9BGoogle
- Score
- 29.2%
Strengths
- Ranks #3 of 7 compared models
- 67th percentile on this benchmark
- C evidence result
Considerations
- This result measures Natural Questions, not total model capability
- 04GOGemma 3n E4BGoogle
- Score
- 20.9%
- Speed
- Up to 42 tok/s via Together
Strengths
- Ranks #4 of 7 compared models
- 50th percentile on this benchmark
- C evidence result
Considerations
- This result measures Natural Questions, not total model capability
- 05
- Score
- 20.9%
Strengths
- Ranks #5 of 7 compared models
- 33th percentile on this benchmark
- C evidence result
Considerations
- This result measures Natural Questions, not total model capability
Selection summary
Best AI Models for Natural Questions
Gemma 2 27B currently leads Natural Questions with 34.5%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
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. It contains 307,373 training examples where annotators provide long answers (passages) and short answers (entities) from Wikipedia pages, or mark them as unanswerable.
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
- Yes
- Evaluation key
- natural-questions|llm-stats-current
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 34.5%.
What does Natural Questions measure?
Natural Questions is a question answering dataset featuring real anonymized queries issued to Google search engine. It contains 307,373 training examples where annotators provide long answers (passages) and short answers (entities) from Wikipedia pages, or mark them as unanswerable.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
7 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.