K2V Study - PhyGenBench Average: leaderboard

The K2V paper evaluates video-generation models and explicit generation pipelines on physical plausibility. PhysicsIQ and PhyGen metrics retain their own scales and cohorts. Training-free keyframe pipelines and centre-frame ablations remain separate configurations of their underlying models. This board reports phyGenEval PCA (0-1). Higher is better.

Metric: PhyGenEval PCA (0-1). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 8 models tracked. Updated 14 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1K2V+Wan2.2-14BEvaluation run: K2V Gemini 3.8 Flash plus Gemini 3.1 Flash Image0.633
2K2V+Wan2.2-5BEvaluation run: K2V Gemini 3.8 Flash plus Gemini 3.1 Flash Image0.633
3Wan2.2-TI2V-5B0.544
4Wan2.2-T2V-A14B0.527
5CogVideoX-5B0.45
6Vchitect 2.0 (2B)0.45
7Open-Sora V1.2 (1.1B)0.44
8Cosmos-Predict2.50.352

Interactive version: theaggregate.ai/benchmark?slug=k2v-study-phygenbench-average · How It Works · Data refreshed daily, snapshot 2026-11-16.