video-world-model
ReasoningStructureTestset
Reasoning-Structured Videos
Updated 17 September 2026: corrected release description and added the latest completed R20/R50 evaluations.
A stratified diagnostic suite for compositional consistency in action-conditioned video world models.
Reasoning-Structured Videos is a deterministic Unreal Engine 5 video benchmark in which trajectories are organised as rooted graphs rather than as independent clips. The graph construction exposes three path-level relations that a faithful… See the full description on the dataset page: https://huggingface.co/datasets/VideoWorldmodel/ReasoningStructureTestset.Evaluation
Reasoning-Structured Videos: Evaluation Artifacts
This page hosts evaluation artifacts for Reasoning-Structured Videos: A Stratified Diagnostic Suite for Compositional Consistency in World Models.
The benchmark tests whether action-conditioned video world models respect three trajectory relations:
Inverse: a path followed by its inverse should return to the initial state.
Loop: a closed path should return to the initial state.
Equivalence: two different paths reaching the same… See the full description on the dataset page: https://huggingface.co/datasets/VideoWorldmodel/Evaluation.ReasoningVideoSamples