Wan 3.0
#1 in the Artificial Analysis text-to-video arena.
Wan 3.0 is Alibaba’s latest video generation model and currently tops the Artificial Analysis text-to-video arena.
- Provider
- Alibaba (Qwen)
- Type
- Video model
- Released
- Aug 19, 2026
- Price
- ≈$12 per minute of video
- Input
- text, image
- Output
- video
- Open weights
- No
Best for
- Multimodal
- Image generation
Strengths
- #1 video arena Elo
- Lower price than most top-5 rivals
More from Alibaba (Qwen)
- Qwen3.8 Max — Alibaba (Qwen). Alibaba’s 2.4T-parameter proprietary flagship with video understanding.
- Qwen3.8 2.4T A95B — Alibaba (Qwen). The open-weight variant of Qwen3.8 Max — the largest open model available.
- Qwen3.8 Flash — Alibaba (Qwen). Open multimodal reasoning model for coding, desktop interaction and long video.
- Qwen3.6 35B A3B — Alibaba (Qwen). Tiny-active-parameter open MoE — a local-inference favorite.
- Qwen3-Embedding-8B — Alibaba (Qwen). Leading open-weight multilingual embedding model.
- Qwen-Image-3.0-Pro — Alibaba (Qwen). Alibaba’s flagship image model with strong text rendering.
- Qwen-Image-2.1 — Alibaba (Qwen). Highest-ranked open-weight image model in the arena.
- Qwen-Audio-3.1-TTS-Plus — Alibaba (Qwen). Top-3 voice quality at a quarter of the leader’s price.