Is Your Driving World Model an All-Around Player?

TL;DR

WorldLens introduces a comprehensive benchmark, dataset, and evaluator to assess the realism of driving world models across visual, geometric, behavioral, and perceptual dimensions.

Contribution

It provides a unified framework to evaluate and compare driving world models on multiple fidelity aspects, bridging the gap between visual quality and realistic behavior.

Findings

No existing model excels across all fidelity axes.

Texture-rich models often violate geometric consistency.

Behaviorally faithful models lack visual realism.

Abstract

Today's driving world models can generate remarkably realistic dash-cam videos, yet no single model excels universally. Some generate photorealistic textures but violate basic physics; others maintain geometric consistency but fail when subjected to closed-loop planning. This disconnect exposes a critical gap: the field evaluates how real generated worlds appear, but rarely whether they behave realistically. We introduce WorldLens, a unified benchmark that measures world-model fidelity across the full spectrum, from pixel quality and 4D geometry to closed-loop driving and human perceptual alignment, through five complementary aspects and 24 standardized dimensions. Our evaluation of six representative models reveals that no existing approach dominates across all axes: texture-rich models violate geometry, geometry-aware models lack behavioral fidelity, and even the strongest performers achieve only 2-3 out of 10 on human realism ratings. To bridge algorithmic metrics with human perception, we further contribute WorldLens-26K, a 26,808-entry human-annotated preference dataset pairing numerical scores with textual rationales, and WorldLens-Agent, a vision-language evaluator distilled from these judgments that enables scalable, explainable auto-assessment. Together, the benchmark, dataset, and agent form a unified ecosystem for assessing generated worlds not merely by visual appeal, but by physical and behavioral fidelity.