Open-source text-to-image models ranked by Image Arena preference, GenEval, HPS v2, and more.
Benchmark data last synced May 7, 2026
| Compare | ||||||
|---|---|---|---|---|---|---|
AA72.9 | Bytedance | 88 | — | 14B(7B active) | 4.8 GB | |
BB67.6 | Alibaba | 0 | — | 6B | 4.2 GB | |
BB59.4 | Stability AI | 0 | 1024×1024 | 8.1B | 5.5 GB | |
BB58.1 | Black Forest Labs | 0 | — | 9B | 6.0 GB | |
CC54.4 | Black Forest Labs | 0 | — | 12B | 7.9 GB | |
CC53.8 | StepFun | 0 | — | 0B | 0.5 GB | |
CC52.7 | Tencent | 0 | 2048×2048 | 80B(13B active) | 8.5 GB | |
CC50.3 | Black Forest Labs | 0 | 4MP | 32B | 20.1 GB | |
CC47.4 | Alibaba | 0 | 2048×2048 | 20B | 12.8 GB | |
CC46.8 | Alibaba | 0 | — | 20B | 12.8 GB | |
CC45.2 | Alibaba | 0 | — | 20B | 12.8 GB | |
CC44.3 | Black Forest Labs | 0 | — | 4B | 3.0 GB | |
CC41.5 | Black Forest Labs | 0 | — | 12B | 7.9 GB | |
DD35.5 | Tencent | 0 | — | 80B(13B active) | 8.5 GB | |
DD34.3 | Z.ai | 0 | — | 16B | 10.3 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.
Model Families
Every model series we track, grouped by family. See every Llama, Qwen, GPT, Claude, Gemini, and beyond on a single page.
