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
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | K2V+Wan2.2-14B | Evaluation run: K2V Gemini 3.8 Flash plus Gemini 3.1 Flash Image | 55 | |
| 2 | K2V+Wan2.2-5B | Evaluation run: K2V Gemini 3.8 Flash plus Gemini 3.1 Flash Image | 50 | |
| 3 | Cosmos3-Super | 42.7 | #169 | |
| 4 | MiniMax H3 (FL2VA) | 39.8 | ||
| 5 | Cosmos3-Nano | 37.3 | #303 | |
| 6 | MiniMax H3 Max | 36.2 | ||
| 7 | Grok Imagine Video | 34.8 | ||
| 8 | Magi-1 24B | Evaluation run: GeoPhys best-of-16; original prompt | 33.7 | |
| 9 | Cosmos3-Edge | 32.7 | ||
| 10 | Wan2.2-14B | 32.2 | ||
| 11 | CogVideoX-5B-I2V | 31.8 | ||
| 12 | Kandinsky-WM 1.0 | 30.8 | ||
| 13 | Wan2.2-TI2V-5B | 27.7 | ||
| 14 | Sora 2 | 26.5 | ||
| 15 | P-Video | 25.3 |
Interactive version: theaggregate.ai/benchmark?slug=k2v-study-physics-iq-verified-image-to-video · How It Works · Data refreshed daily, snapshot 2026-11-16.