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

TL;DR

WorldArena introduces a comprehensive benchmark for evaluating embodied world models across perceptual and functional aspects, revealing gaps between visual quality and task performance, and providing a unified metric and public leaderboard.

Contribution

The paper presents WorldArena, a unified benchmark with multi-dimensional evaluation metrics and a holistic score, addressing the fragmented evaluation of embodied world models.

Findings

High perception quality does not guarantee strong task performance.

The benchmark reveals a significant perception-functionality gap.

Extensive experiments on 14 models demonstrate the framework's effectiveness.

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://world-arena.ai, providing a framework for tracking progress toward truly functional world models in embodied AI.