OpenArt Arena launches expert-led leaderboard ranking image and video models by real creative work
chrisfirst · x · 2026-09-16
OpenArt launched Arena, a leaderboard that ranks image and video models by the actual creative work they're used for rather than a single "best model" claim:
- Blind testing: model names hidden, creators pick between two outputs on real creative criteria — no logos or reputation bias
- Use-case boards: video split into overall, ads, film, animation, motion design, video editing, lip sync; image split into e-commerce, film, graphic design, image editing
- Criteria: prompt adherence, aesthetics, consistency, creativity, reference adherence
In the current overall video board (v1.0): Seedance 2.5 (ByteDance) leads at 1125, followed by Wan 3.0 (Alibaba, 1047) and Seedance 2.0; Google Omni Flash, Flux 3 Video, MiniMax H3, Kling 3.0 Omni and Grok Imagine 1.5 round out the top 10. Seedance models also top the ads, film and animation boards.
More from Multimodal
- Fable 5.5 xhigh renders detailed stacked-bears image in just 21 minutes — legit_api · 2026-11-02
- Audio8-TTS-Realistic-Air, a zero-shot voice-cloning TTS model, trends on Hugging Face — Edge0 · 2026-11-02
- Mistral explains why its model-built solver is a first step toward new drugs and batteries — MistralAI · 2026-11-02
- Mistral Large 4 writes a quantum chemistry SCF solver from scratch with one short prompt — MistralAI · 2026-11-02
- Gorgeous dithered pixel art collage serves up a 'great morning' — philipvollet · 2026-11-02
- Clown Prophecy moves to new repo, now uses first clip as reference to fix H3 quality drift — reeight · 2026-11-02