WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models

TL;DR

WorldArena addresses the lack of a unified benchmark for embodied world models by evaluating both perceptual fidelity and functional utility. It introduces a comprehensive evaluation framework with 16 video-quality metrics across 6 sub-dimensions, plus embodied-task evaluations (data engine, policy evaluator, action planner) and human judgments, all integrated by the EWMScore. An empirical study across 14 models on the RobotTwin 2.0 dataset reveals a persistent perception–task-performance gap, showing that high visual fidelity does not guarantee strong embodied decision-making. The EWMScore strongly aligns with human judgments ($r = 0.825$) and provides a practical index to monitor progress toward truly functional embodied world models.

Abstract

While world models have emerged as a cornerstone of embodied intelligence by enabling agents to reason about environmental dynamics through action-conditioned prediction, their evaluation remains fragmented. Current evaluation of embodied world models has largely focused on perceptual fidelity (e.g., video generation quality), overlooking the functional utility of these models in downstream decision-making tasks. In this work, we introduce WorldArena, a unified benchmark designed to systematically evaluate embodied world models across both perceptual and functional dimensions. WorldArena assesses models through three dimensions: video perception quality, measured with 16 metrics across six sub-dimensions; embodied task functionality, which evaluates world models as data engines, policy evaluators, and action planners integrating with subjective human evaluation. Furthermore, we propose EWMScore, a holistic metric integrating multi-dimensional performance into a single interpretable index. Through extensive experiments on 14 representative models, we reveal a significant perception-functionality gap, showing that high visual quality does not necessarily translate into strong embodied task capability. WorldArena benchmark with the public leaderboard is released at https://worldarena.ai, providing a framework for tracking progress toward truly functional world models in embodied AI.

Figures (12)

• Figure 1:
• Figure 2:
• Figure 4: Illustrations of the video quality evaluations across six dimensions: visual quality, motion quality, content consistency, physics adherence, 3D accuracy, and controllability.
• Figure 5: Overview of the embodied task evaluation systems, including the assessment of world models as embodied data engines (measuring success rate of trained downstream policies), policy evaluators (measuring correlation between world model and real-world evaluation results), and action planners (measuring success rate of world model-based policies).
• Figure 6: Correlation of policy evaluation results from world models and the physical simulator.