physics benchmark
PIQA
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 11, 2026
Models11
Model coverage11
MetricScore
EvidenceB
PIQA Ranking
Higher score ranks better on this benchmark.
| 01 | MI | 88.6% | 100.0% | 11 | C | |
| 02 | NR | 84.4% | 90.0% | 11 | C | |
| 03 | GO | 83.2% | 80.0% | 11 | C | |
| 04 | GO | 81.7% | 70.0% | 11 | C | |
| 05 | GO | 81.0% | 60.0% | 11 | C | |
| 06 | GO | 81.0% | 50.0% | 11 | C | |
| 07 | MI | 81.0% | 40.0% | 11 | C | |
| 08 | GO | 78.9% | 30.0% | 11 | C | |
| 09 | GO | 78.9% | 20.0% | 11 | C | |
| 10 | MI | 77.6% | 10.0% | 11 | C | |
| 11 | BA | 55.2% | 0.0% | 11 | C |
PIQA Score Distribution
A closer view of the leading scores on this benchmark.
PIQA Highlights
The leading models and scores on this benchmark.
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.