ViGoR-Bench (Video) - Process Reasoning Accuracy: leaderboard
Metric: Process reasoning accuracy (0-100 judge score): how far the generated frames progress toward the correct solution, 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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Sora 2 Pro | 34.8 | |
| 2 | Veo 3 | 31.9 | |
| 3 | Kling 1.6 | 9.6 | |
| 4 | Seedance 1.0 Pro | 9.2 | |
| 5 | Wan 2.2 | 7.4 |
Interactive version: theaggregate.ai/benchmark?slug=vigor-bench-video-process-reasoning-accuracy · How It Works · Data refreshed daily, snapshot 2026-10-11.