WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models

WorldRoamBench is a new open-world benchmark for evaluating the long-horizon stability of interactive world models, addressing limitations in existing benchmarks. It assesses models across four dimensions: action, vision, physics, and memory, and reveals that none of the tested models reliably satisfy all dimensions.

RSS Score 0 9/18/2026, 4:00:00 AM Original Source
Save an API key to vote.