ViGoR-Bench (Video) - Rule Obey: leaderboard

Metric: Rule-obey rate (%): share of final video frames that follow the instruction's explicit constraints, over ViGoR-Bench's 918 generative visual-reasoning tasks (physical, knowledge and symbolic reasoning: sorting, assembly, Sudoku, mazes, jigsaws, equations, function plots and more), judged by Gemini-2.5-Pro against the human-verified reference image or answer; image-to-video generation; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 5 models tracked.

Top models

#ModelScoreOverall rank
1Sora 2 Pro16.6
2Veo 315
3Seedance 1.0 Pro14
4Wan 2.26.4
5Kling 1.66.3

Interactive version: theaggregate.ai/benchmark?slug=vigor-bench-video-rule-obey · How It Works · Data refreshed daily, snapshot 2026-10-11.