# PHYRE: A New Benchmark for Physical Reasoning

arXiv: https://arxiv.org/abs/1908.05656 · HTML: https://mlsanity.com/paper/1908.05656/

## Key facts

- Cited by 137 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Aug 2019.

## Built on by (most cited first, 30 of 137)

- [How Far is Video Generation from World Model: A Physical Law Perspective](https://mlsanity.com/paper/2411.02385/) (2024)
- [Physion: Evaluating Physical Prediction from Vision in Humans and Machines](https://mlsanity.com/paper/2106.08261/) (2021)
- [VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation](https://mlsanity.com/paper/2503.06800/) (2025)
- [SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models](https://mlsanity.com/paper/2210.05861/) (2022)
- [Mind's Eye: Grounded Language Model Reasoning through Simulation](https://mlsanity.com/paper/2210.05359/) (2022)
- [Generalization on the Unseen, Logic Reasoning and Degree Curriculum](https://mlsanity.com/paper/2301.13105/) (2023)
- [Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning](https://mlsanity.com/paper/2103.16564/) (2021)
- [ComPhy: Compositional Physical Reasoning of Objects and Events from Videos](https://mlsanity.com/paper/2205.01089/) (2022)
- [Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language](https://mlsanity.com/paper/2110.15358/) (2021)
- [Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning](https://mlsanity.com/paper/2107.00848/) (2021)
- [IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments](https://mlsanity.com/paper/2506.09849/) (2025)
- [PROST: Physical Reasoning of Objects through Space and Time](https://mlsanity.com/paper/2106.03634/) (2021)
- [Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems](https://mlsanity.com/paper/2504.02918/) (2025)
- [NEWTON: Are Large Language Models Capable of Physical Reasoning?](https://mlsanity.com/paper/2310.07018/) (2023)
- [Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks](https://mlsanity.com/paper/2410.23208/) (2024)
- [A Benchmark for Compositional Visual Reasoning](https://mlsanity.com/paper/2206.05379/) (2022)
- [AGENT: A Benchmark for Core Psychological Reasoning](https://mlsanity.com/paper/2102.12321/) (2021)
- [Benchmarks for Automated Commonsense Reasoning: A Survey](https://mlsanity.com/paper/2302.04752/) (2023)
- [Visual cognition in multimodal large language models](https://mlsanity.com/paper/2311.16093/) (2023)
- [Physical Design using Differentiable Learned Simulators](https://mlsanity.com/paper/2202.00728/) (2022)
- [How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad](https://mlsanity.com/paper/2406.06467/) (2024)
- [CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models](https://mlsanity.com/paper/2506.09943/) (2025)
- [Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions](https://mlsanity.com/paper/2205.13803/) (2022)
- [MacGyver: Are Large Language Models Creative Problem Solvers?](https://mlsanity.com/paper/2311.09682/) (2023)
- [A Review of Emerging Research Directions in Abstract Visual Reasoning](https://mlsanity.com/paper/2202.10284/) (2022)
- [Causal-JEPA: Learning World Models through Object-Level Latent Masking](https://mlsanity.com/paper/2602.11389/) (2026)
- [Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation](https://mlsanity.com/paper/2506.21876/) (2025)
- [Interpreting Physics in Video World Models](https://mlsanity.com/paper/2602.07050/) (2026)
- [Capturing the objects of vision with neural networks](https://mlsanity.com/paper/2109.03351/) (2021)
- [A Survey on Machine Learning Approaches for Modelling Intuitive Physics](https://mlsanity.com/paper/2202.06481/) (2022)

## Abstract (arXiv)

Understanding and reasoning about physics is an important ability of intelligent agents. We develop the PHYRE benchmark for physical reasoning that contains a set of simple classical mechanics puzzles in a 2D physical environment. The benchmark is designed to encourage the development of learning algorithms that are sample-efficient and generalize well across puzzles. We test several modern learning algorithms on PHYRE and find that these algorithms fall short in solving the puzzles efficiently. We expect that PHYRE will encourage the development of novel sample-efficient agents that learn efficient but useful models of physics. For code and to play PHYRE for yourself, please visit https://player.phyre.ai.