Wan 3.0
Alibaba's Wan 3.0 video model, offered through Alibaba Cloud Model Studio, with clips of up to 30 seconds at up to 1080p. It is first on Artificial Analysis' text-to-video arena and ties for first on LMArena image-to-video.
Alibaba (Wan)Video modelReleased August 2026Data checked October 18, 2026
Where people rank it
#1
Turning images into video (tied), 3,442 votes
#3
Creating video (tied), 2,598 votes
From blind votes on LMArena, where people pick the better of two anonymous answers. See the full tables on the AI leaderboard.
Strengths and weaknesses
- First on the Artificial Analysis text-to-video arena
- Tied for first on LMArena image-to-video
- Clear per-second pricing ($0.10 per second at 720p in Alibaba Cloud's Singapore region)
- Only sixth among all entries on LMArena text-to-video
- Not open-weight, unlike earlier Wan releases
Best for
- Longer clips of up to 30 seconds
- Animating images into video
Every score we have
Each bar compares this model with the best result any model on this page has on the same test.
- LMArena text to video1,476.3Arena score 1476.3 (95% CI 1463.6 to 1488.9); 2,598 votes; entry "wan3.0"; position 6 of 48 on the full board
- LMArena image to video1,479.8Arena score 1479.8 (95% CI 1469.0 to 1490.6); 3,442 votes; entry "wan3.0"; position 3 of 48 on the full board
- Artificial Analysis video arena1,174Elo 1174.0 (95% CI 1159.0 to 1189.0); 5,861 appearances; position 1 of 32 on the Artificial Analysis text-to-video arena
- Price per minute of video (estimate)$12$12.00 per minute of video (Artificial Analysis estimate)
Compare with
- Gemini Omni FlashGoogle's Omni video model, first shown at I/O 2026, which generates and edits video with native audio; the 1.1 Flash version became generally available in the Gemini API on August 27, 2026.
- MiniMax H3MiniMax's open-weight omni-modal video model, which generates 4 to 15 second clips with native stereo audio from text, images, video and audio.
- FLUX 3 VideoBlack Forest Labs' FLUX 3 video model, which generates video with synchronized audio from text, keyframes or an existing clip.
- Grok Imagine Video 1.5SpaceXSI's (formerly xAI) Grok Imagine video model, which turns text or images into short videos.