physics benchmark
PIQA Leaderboard
PIQA (Physical Interaction: Question Answering) is a benchmark dataset for physical commonsense reasoning in natural language. It tests AI systems' ability to answer questions requiring physical world knowledge through multiple choice questions with everyday situations, focusing on atypical solutions inspired by instructables.com. The dataset contains 21,000 multiple choice questions where models must choose the most appropriate solution for physical interactions.
Updated Aug 17, 2026
Models11
Model coverage11
MetricScore
EvidenceB
PIQA Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score88.6% | Percentile100.0% | Participants11 | EvidenceC | Evaluated |
| Rank02 | ModelNR | Score84.4% | Percentile90.0% | Participants11 | EvidenceC | Evaluated |
| Rank03 | ModelGO | Score83.2% | Percentile80.0% | Participants11 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score81.7% | Percentile70.0% | Participants11 | EvidenceC | Evaluated |
| Rank05 | ModelGO | Score81.0% | Percentile60.0% | Participants11 | EvidenceC | Evaluated |
| Rank06 | ModelGO | Score81.0% | Percentile50.0% | Participants11 | EvidenceC | Evaluated |
| Rank07 | ModelMI | Score81.0% | Percentile40.0% | Participants11 | EvidenceC | Evaluated |
| Rank08 | ModelGO | Score78.9% | Percentile30.0% | Participants11 | EvidenceC | Evaluated |
| Rank09 | ModelGO | Score78.9% | Percentile20.0% | Participants11 | EvidenceC | Evaluated |
| Rank10 | ModelMI | Score77.6% | Percentile10.0% | Participants11 | EvidenceC | Evaluated |
| Rank11 | ModelBA | Score55.2% | Percentile0.0% | Participants11 | EvidenceC | Evaluated |
PIQA Highlights
The leading models and scores on this benchmark.
PIQA Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for PIQA
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis piqa 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.
- 01MIPhi-3.5-MoE-instructMicrosoft
- Score
- 88.6%
Strengths
- Ranks #1 of 11 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures PIQA, not total model capability
- 02NRHermes 3 70BNous Research
- Score
- 84.4%
Strengths
- Ranks #2 of 11 compared models
- 90th percentile on this benchmark
- C evidence result
Considerations
- This result measures PIQA, not total model capability
- 03GOGemma 2 27BGoogle
- Score
- 83.2%
Strengths
- Ranks #3 of 11 compared models
- 80th percentile on this benchmark
- C evidence result
Considerations
- This result measures PIQA, not total model capability
- 04GOGemma 2 9BGoogle
- Score
- 81.7%
Strengths
- Ranks #4 of 11 compared models
- 70th percentile on this benchmark
- C evidence result
Considerations
- This result measures PIQA, not total model capability
- 05GOGemma 3n E4BGoogle
- Score
- 81.0%
- Speed
- Up to 42 tok/s via Together
Strengths
- Ranks #5 of 11 compared models
- 60th percentile on this benchmark
- C evidence result
Considerations
- This result measures PIQA, not total model capability
Selection summary
Best AI Models for PIQA
Phi-3.5-MoE-instruct currently leads PIQA with 88.6%. 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 PIQA?
What PIQA measures and how its scores work.
PIQA (Physical Interaction: Question Answering) is a benchmark dataset for physical commonsense reasoning in natural language. It tests AI systems' ability to answer questions requiring physical world knowledge through multiple choice questions with everyday situations, focusing on atypical solutions inspired by instructables.com. The dataset contains 21,000 multiple choice questions where models must choose the most appropriate solution for physical interactions.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- PIQA
- Modality
- text
- Primary category
- physics
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- piqa|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about PIQA.
Which model scores highest on PIQA?
Phi-3.5-MoE-instruct is currently ranked first with 88.6%.
What does PIQA measure?
PIQA (Physical Interaction: Question Answering) is a benchmark dataset for physical commonsense reasoning in natural language. It tests AI systems' ability to answer questions requiring physical world knowledge through multiple choice questions with everyday situations, focusing on atypical solutions inspired by instructables.com. The dataset contains 21,000 multiple choice questions where models must choose the most appropriate solution for physical interactions.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
11 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.