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

arXiv 26.2 2026 68.6 benchmark

TLDR

WorldArena benchmark evaluates embodied world models on perception and functional utility, revealing a gap between visual quality and task capability.

Reasoning

The paper introduces a comprehensive benchmark with multiple metrics and human evaluation, addressing a clear gap in evaluation. Strengths include systematic multi-dimensional assessment and a public leaderboard; weaknesses may include limited discussion of limitations or generalizability beyond 14 models.

Read-first score

Read-first score 68.6, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 55.

Recency 8%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 25%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,evaluation,experiment,metric

Topical relevance 42%

78.6

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 141.

Keyword Scores

world model

video world model

interactive world model

world dynamics prediction

generative world model

model-based reinforcement learning world model

world simulator

Deep Analysis

Innovations

Unified benchmark for evaluating embodied world models across both perceptual and functional dimensions
Three-dimensional evaluation framework: video perception quality (16 metrics across six sub-dimensions), embodied task functionality (data engine, policy evaluator, action planner with subjective human evaluation)
EWMScore, a holistic metric integrating multi-dimensional performance into a single interpretable index

Methodology

WorldArena is a benchmark that systematically evaluates embodied world models through three dimensions: video perception quality measured with 16 metrics across six sub-dimensions, and embodied task functionality assessing models as data engines, policy evaluators, and action planners with subjective human evaluation. The benchmark includes extensive experiments on 14 representative models and introduces EWMScore as a unified metric.

Key Results

The experiments reveal a significant perception-functionality gap, showing that high visual quality does not necessarily translate into strong embodied task capability.

Resources

Paper