Text-to-video and image-to-video models ranked by Video Arena preference and VBench.
Benchmark data last synced Sep 24, 2026
| Compare | |||||||
|---|---|---|---|---|---|---|---|
CC50.7 | Genmo AI | 39 | — | — | 10B | 6.6 GB | |
CC42.5 | Alibaba | 40 | 720p | 5s | 27B(14B active) | 9.1 GB | |
CC41.9 | Kandinsky | 35 | 768px | 10s | 2B | 1.7 GB | |
DD36.8 | Lightricks | 27 | 3840×2160 | 20s | 19B | 12.1 GB | |
DD35.1 | Tencent | 8 | 720p | — | 0B | 0.5 GB | |
DD34.0 | Kandinsky | 53 | 1408px | 10s | 19B | 12.1 GB |

Model Providers
Every AI lab that ships models we track, ranked by model count, average score, and frontier presence. Compare OpenAI, Anthropic, Meta, Google, Alibaba, and more.
Browse Providers
Every model series we track, grouped by family. See every Llama, Qwen, GPT, Claude, Gemini, and beyond on a single page.