Preprint
Aug 2026
WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity
WorldExam is introduced, a hierarchical diagnostic benchmark spanning four levels: Visual Quality, Control Adherence, Spatial Consistency, and World Reactivity, which supports unified evaluation of camera-, action-, and language-driven model paradigms.
Yuxue Yang, Shu-Yao Shang, Jiahe Wang et al.
· 2 citations