AI Model Leaderboards
AI Video Model Elo Ranking · China
AI video models ranked by Artificial Analysis's text-to-video arena Elo: a relative score from head-to-head battles, comparable only within this board. Synced once a day.
1,335Qwen: Wan 3.0Wan 3.095% CI ±12
1,302MiniMax: MiniMax H3MiniMax H395% CI ±10
1,286Alibaba: HappyHorse-1.0HappyHorse-1.095% CI ±8
- 41,272Alibaba: HappyHorse-1.1HappyHorse-1.1
95% CI ±9
- 5
1,259 - 61,243Qwen: Wan2.7-260612Wan2.7-260612
95% CI ±9
- 7
1,230 - 81,230
- 9
1,230PixVerse: PixVerse V5.6PixVerse V5.695% CI ±8
- 101,230PixVerse: PixVerse V6PixVerse V6
95% CI ±8
- 11
1,225Vidu: Vidu Q3 ProVidu Q3 Pro95% CI ±8
- 121,219PixVerse: PixVerse V5.5PixVerse V5.5
95% CI ±10
- 131,215
- 14
1,211Skywork AI: SkyReels V4SkyReels V495% CI ±9
- 151,210
- 161,210Qwen: Wan 2.7Wan 2.7
95% CI ±9
- 171,203
- 181,197Qwen: Wan 2.6Wan 2.6
95% CI ±9
- 191,196
95% CI ±8
- 201,193
95% CI ±8
- 211,185
- 221,184
- 231,176MiniMax: Hailuo 2.3Hailuo 2.3
95% CI ±8
- 241,176PixVerse: PixVerse V5PixVerse V5
95% CI ±8
- 251,176
- 261,171Vidu: Vidu Q2Vidu Q2
95% CI ±8
- 271,170MiniMax: Hailuo 02 StandardHailuo 02 Standard
95% CI ±9
- 281,160Qwen: Wan 2.5 PreviewWan 2.5 Preview
95% CI ±8
- 291,154MiniMax: Hailuo 02 ProHailuo 02 Pro
95% CI ±9
- 301,136
95% CI ±8
- 311,116Qwen: Wan 2.2 A14BWan 2.2 A14B
95% CI ±8
- 321,105Vidu: Vidu Q3 TurboVidu Q3 Turbo
95% CI ±11
- 331,092
95% CI ±9
- 341,084
- 351,083PixVerse: PixVerse V4.5PixVerse V4.5
95% CI ±10
- 361,032
95% CI ±9
- 371,026MiniMax: T2V-01T2V-01
95% CI ±8
- 381,024MiniMax: T2V-01-DirectorT2V-01-Director
95% CI ±9
- 39
1,020Tencent: HunyuanVideo-1.5HunyuanVideo-1.595% CI ±9
- 401,018
95% CI ±9
- 411,018Qwen: Wan 2.1 14BWan 2.1 14B
95% CI ±9
- 421,010
- 431,002Vidu: Vidu Q1Vidu Q1
95% CI ±11
- 44992Tencent: Hunyuan VideoHunyuan Video
95% CI ±9
- 45950Qwen: Wan 2.2 5BWan 2.2 5B
95% CI ±10
- 46949
95% CI ±9
- 47
904StepFun: Step-Video-T2VStep-Video-T2V95% CI ±11
- 48
805Z.ai: CogVideoX-5BCogVideoX-5B95% CI ±10
Source: Artificial Analysis · arena Elo rating, as of Sep 30, 2026. Elo comes from head-to-head arena battles rather than a fixed exam, so it is a relative score: it only compares within the same board, and it gets steadier as more battles come in.
Arena ratings come from Artificial Analysis's public evaluations and sync once a day; scores for brand-new models move around more until enough battles are in. Names link to the matching tool page on our site.
The China board groups models by where the team is based (Alibaba, ByteDance, Tencent, Baidu, DeepSeek, Moonshot, Zhipu, MiniMax, StepFun and others), not by the model's language or where it is hosted. Everything else counts as overseas, so this board has fewer entries than the global one.
Disclaimer: this board is generated automatically from third-party public data, for reference only, with no warranty or recommendation and no view on any product's safety or legality; names and trademarks belong to their respective owners, and we are not affiliated with or endorsed by these products. To report an error or ask for a correction or removal, use the contact details on our cooperation page to reach us. By using this site you accept our Terms of Service and Privacy Policy, and we accept no liability for any loss arising from use of this board.