physics benchmark
GPQA Physics
Physics subset of GPQA, containing challenging multiple-choice questions written by domain experts in physics. These Google-proof questions require graduate-level knowledge and reasoning.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
GPQA Physics Ranking
Higher score ranks better on this benchmark.
| 01 | OP | 92.8% | 100.0% | 1 | C |
GPQA Physics Highlights
The leading models and scores on this benchmark.
What is GPQA Physics?
What GPQA Physics measures and how its scores work.
Physics subset of GPQA, containing challenging multiple-choice questions written by domain experts in physics. These Google-proof questions require graduate-level knowledge and reasoning.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- GPQA Physics
- Modality
- text
- Primary category
- physics
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- gpqa-physics|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about GPQA Physics.
Which model scores highest on GPQA Physics?
o1 is currently ranked first with 92.8%.
What does GPQA Physics measure?
Physics subset of GPQA, containing challenging multiple-choice questions written by domain experts in physics. These Google-proof questions require graduate-level knowledge and reasoning.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.