- Services
Text-to-video and image-to-video models ranked by Video Arena preference and VBench.
Benchmark data last synced Oct 10, 2026
| Compare | |||||||
|---|---|---|---|---|---|---|---|
CC54.9 | Genmo AI | 48 | — | — | 10B | 6.6 GB | |
CC50.5 | Alibaba | 0 | 480p, 720p | — | 14B | 9.1 GB | |
CC48.8 | PrismNew Tencent Hunyuan | 0 | 2K | — | 0B | 0.5 GB | |
CC48.6 | 智谱AI | 0 | 1360x768 | 10s | 5B | 3.6 GB | |
CC47.3 | Kandinsky Lab | 0 | 1920x1080 | 5s | 3B | 2.3 GB | |
CC46.0 | Tencent | 17 | 720p | — | 0B | 0.5 GB | |
CC45.4 | Alibaba | 44 | 720p | 5s | 27B(14B active) | 9.1 GB | |
CC45.0 | Sber | 0 | Full-HD (1920x1080) | 5s | 0B | 0.5 GB | |
Ad Tools for AI BuildersAll the hardware and tools you need to run private AI at your office or at home.Shop Now | |||||||
CC44.5 | SGF+New Tsinghua University and JD Joy Future Academy | 0 | — | 86400s | 0B | 0.5 GB | |
CC44.1 | Kandinsky | 47 | 768px | 10s | 2B | 1.7 GB | |
CC41.3 | Lightricks | 32 | 3840×2160 | 20s | 19B | 12.1 GB | |
DD39.6 | Kandinsky | 62 | 1408px | 10s | 19B | 12.1 GB | |
DD37.5 | Kandinsky Lab | 0 | 1920x1080 | 5s | 29B | 18.3 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.
