# T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation

arXiv: https://arxiv.org/abs/2505.00337 · HTML: https://mlsanity.com/paper/2505.00337/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 58 references that are in the map.
- First posted on arXiv 1 May 2025.

## Builds on (most cited first, 30 of 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [Structure and Content-Guided Video Synthesis with Diffusion Models](https://mlsanity.com/paper/2302.03011/) (2023)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [Learning Universal Policies via Text-Guided Video Generation](https://mlsanity.com/paper/2302.00111/) (2023)
- [Physics-informed neural networks (PINNs) for fluid mechanics: A review](https://mlsanity.com/paper/2105.09506/) (2021)
- [Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations](https://mlsanity.com/paper/1711.10561/) (2017)
- [ControlVideo: Training-free Controllable Text-to-Video Generation](https://mlsanity.com/paper/2305.13077/) (2023)
- [Flexible Diffusion Modeling of Long Videos](https://mlsanity.com/paper/2205.11495/) (2022)
- [VideoPhy: Evaluating Physical Commonsense for Video Generation](https://mlsanity.com/paper/2406.03520/) (2024)
- [T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation](https://mlsanity.com/paper/2407.14505/) (2024)
- [Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation](https://mlsanity.com/paper/2410.05363/) (2024)
- [Panacea: Panoramic and Controllable Video Generation for Autonomous Driving](https://mlsanity.com/paper/2311.16813/) (2023)
- [Video Generation From Text](https://mlsanity.com/paper/1710.00421/) (2017)
- [Align and Prompt: Video-and-Language Pre-training with Entity Prompts](https://mlsanity.com/paper/2112.09583/) (2021)
- [Vision Language Models in Autonomous Driving: A Survey and Outlook](https://mlsanity.com/paper/2310.14414/) (2023)
- [FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation](https://mlsanity.com/paper/2311.01813/) (2023)

## Built on by (most cited first, 30 of 39)

- [World Simulation with Video Foundation Models for Physical AI](https://mlsanity.com/paper/2511.00062/) (2025)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [RoboScape: Physics-informed Embodied World Model](https://mlsanity.com/paper/2506.23135/) (2025)
- [Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations](https://mlsanity.com/paper/2507.00990/) (2025)
- ["PhyWorldBench": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models](https://mlsanity.com/paper/2507.13428/) (2025)
- [Rethinking Video Generation Model for the Embodied World](https://mlsanity.com/paper/2601.15282/) (2026)
- [T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation](https://mlsanity.com/paper/2512.21094/) (2025)
- [T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation](https://mlsanity.com/paper/2507.18107/) (2025)
- [Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting](https://mlsanity.com/paper/2510.04401/) (2025)
- [MBench: A Comprehensive Benchmark on Memory Capability for Video World Models](https://mlsanity.com/paper/2606.00793/) (2026)
- [LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference](https://mlsanity.com/paper/2510.11512/) (2025)
- [Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoning](https://mlsanity.com/paper/2603.19607/) (2026)
- [PhyGround: Benchmarking Physical Reasoning in Generative World Models](https://mlsanity.com/paper/2605.10806/) (2026)
- [Current World Models Lack a Persistent State Core](https://mlsanity.com/paper/2606.20545/) (2026)
- [T2VTextBench: A Human Evaluation Benchmark for Textual Control in Video Generation Models](https://mlsanity.com/paper/2505.04946/) (2025)
- [Do Joint Audio-Video Generation Models Understand Physics?](https://mlsanity.com/paper/2605.07061/) (2026)
- [Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse](https://mlsanity.com/paper/2505.16284/) (2025)
- [Towards High-Order Mean Flow Generative Models: Feasibility, Expressivity, and Provably Efficient Criteria](https://mlsanity.com/paper/2508.07102/) (2025)
- [Objects in Generated Videos Are Slower Than They Appear: Models Suffer Sub-Earth Gravity and Don't Know Galileo's Principle...for now](https://mlsanity.com/paper/2512.02016/) (2025)
- [MoReGen: Multi-Agent Motion-Reasoning Engine for Code-based Text-to-Video Synthesis](https://mlsanity.com/paper/2512.04221/) (2025)
- [Minimalist Softmax Attention Provably Learns Constrained Boolean Functions](https://mlsanity.com/paper/2505.19531/) (2025)
- [Too Easily Fooled? Prompt Injection Breaks LLMs on Frustratingly Simple Multiple-Choice Questions](https://mlsanity.com/paper/2508.13214/) (2025)
- [CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models](https://mlsanity.com/paper/2605.23699/) (2026)
- [PH-Dreamer: A Physics-Driven World Model via Port-Hamiltonian Generative Dynamics](https://mlsanity.com/paper/2605.18303/) (2026)
- [YoCausal: How Far is Video Generation from World Model? A Causality Perspective](https://mlsanity.com/paper/2605.30346/) (2026)
- [Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights](https://mlsanity.com/paper/2512.01816/) (2025)
- [Physically Viable World Models: A Case for Query-Conditioned Embodied AI](https://mlsanity.com/paper/2605.30542/) (2026)
- [The Seriality Gap in Video Diffusion Models](https://mlsanity.com/paper/2607.13031/) (2026)
- [Principia: Relational Physics Tests for Video Models](https://mlsanity.com/paper/2609.04200/) (2026)
- [PhysWeep: Does a Video Generator Realize the Physics You Ask For?](https://mlsanity.com/paper/2609.06207/) (2026)

## Abstract (arXiv)

Text-to-video generative models have made significant strides in recent years, producing high-quality videos that excel in both aesthetic appeal and accurate instruction following, and have become central to digital art creation and user engagement online. Yet, despite these advancements, their ability to respect fundamental physical laws remains largely untested: many outputs still violate basic constraints such as rigid-body collisions, energy conservation, and gravitational dynamics, resulting in unrealistic or even misleading content. Existing physical-evaluation benchmarks typically rely on automatic, pixel-level metrics applied to simplistic, life-scenario prompts, and thus overlook both human judgment and first-principles physics. To fill this gap, we introduce T2VPhysBench, a first-principled benchmark that systematically evaluates whether state-of-the-art text-to-video systems, both open-source and commercial, obey twelve core physical laws including Newtonian mechanics, conservation principles, and phenomenological effects. Our benchmark employs a rigorous human evaluation protocol and includes three targeted studies: (1) an overall compliance assessment showing that all models score below 0.60 on average in each law category; (2) a prompt-hint ablation revealing that even detailed, law-specific hints fail to remedy physics violations; and (3) a counterfactual robustness test demonstrating that models often generate videos that explicitly break physical rules when so instructed. The results expose persistent limitations in current architectures and offer concrete insights for guiding future research toward truly physics-aware video generation.