K2V Study - Physics-IQ Verified Image to Video: 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 physics-IQ Verified score (0-100). Higher is better.

Metric: Physics-IQ Verified score (0-100). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 15 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 Image55
2K2V+Wan2.2-5BEvaluation run: K2V Gemini 3.8 Flash plus Gemini 3.1 Flash Image50
3Cosmos3-Super42.7#169
4MiniMax H3 (FL2VA)39.8
5Cosmos3-Nano37.3#303
6MiniMax H3 Max36.2
7Grok Imagine Video34.8
8Magi-1 24BEvaluation run: GeoPhys best-of-16; original prompt33.7
9Cosmos3-Edge32.7
10Wan2.2-14B32.2
11CogVideoX-5B-I2V31.8
12Kandinsky-WM 1.030.8
13Wan2.2-TI2V-5B27.7
14Sora 226.5
15P-Video25.3

Interactive version: theaggregate.ai/benchmark?slug=k2v-study-physics-iq-verified-image-to-video · How It Works · Data refreshed daily, snapshot 2026-11-16.