WorldModelBench: Judging Video Generation Models As World Models

TL;DR

WorldModelBench is a new benchmark for evaluating video generation models as world models, focusing on physics adherence and decision-making relevance, with a large-scale human-labeled dataset and an automated judger.

Contribution

We introduce WorldModelBench, a comprehensive benchmark that evaluates physics and instruction adherence in video world models, supported by a large human annotation dataset and an improved automated evaluation method.

Findings

WorldModelBench detects subtle physics violations in video models.

Crowd-sourced 67K human labels enable accurate evaluation.

Fine-tuning an automated judger improves violation detection accuracy.

Abstract

Video generation models have rapidly progressed, positioning themselves as video world models capable of supporting decision-making applications like robotics and autonomous driving. However, current benchmarks fail to rigorously evaluate these claims, focusing only on general video quality, ignoring important factors to world models such as physics adherence. To bridge this gap, we propose WorldModelBench, a benchmark designed to evaluate the world modeling capabilities of video generation models in application-driven domains. WorldModelBench offers two key advantages: (1) Against to nuanced world modeling violations: By incorporating instruction-following and physics-adherence dimensions, WorldModelBench detects subtle violations, such as irregular changes in object size that breach the mass conservation law - issues overlooked by prior benchmarks. (2) Aligned with large-scale human preferences: We crowd-source 67K human labels to accurately measure 14 frontier models. Using our high-quality human labels, we further fine-tune an accurate judger to automate the evaluation procedure, achieving 8.6% higher average accuracy in predicting world modeling violations than GPT-4o with 2B parameters. In addition, we demonstrate that training to align human annotations by maximizing the rewards from the judger noticeably improve the world modeling capability. The website is available at https://worldmodelbench-team.github.io.