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.
Phi-3.5-MoE-instruct from Microsoft currently leads the PIQA leaderboard with a score of 0.886 across 11 evaluated AI models.
Phi-3.5-MoE-instruct leads with 88.6%, followed by 
Hermes 3 70B at 84.4% and 
Gemma 2 27B at 83.2%.
Progress Over Time
Interactive timeline showing model performance evolution on PIQA
PIQA Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Microsoft | 60B | — | — | ||
| 2 | Nous Research | 70B | — | — | ||
| 3 | Google | 27B | — | — | ||
| 4 | Google | 9B | — | — | ||
| 5 | Microsoft | 4B | — | — | ||
| 5 | Google | 8B | — | — | ||
| 5 | 2B | — | — | |||
| 8 | 2B | — | — | |||
| 8 | Google | 8B | — | — | ||
| 10 | Microsoft | 4B | — | — | ||
| 11 |  Baidu | 21B | — | — |
FAQ
Common questions about PIQA.
Sub-benchmarks
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions