A 1,253-example benchmark for knowledge- and reasoning-intensive science video generation, with expert rubrics, shows large gaps between perceptual realism and scientific correctness in 16 frontier models.
VideoPhy: Evaluating Physical Commonsense for Video Generation , booktitle =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
A 1,253-example benchmark for knowledge- and reasoning-intensive science video generation, with expert rubrics, shows large gaps between perceptual realism and scientific correctness in 16 frontier models.