Wan V2.2 A14B
LMArena ID: wan-v2.2-a14b
AlibabaOpenApache 2.0
Wan V2.2 A14B is an AI video model from Alibaba. On LMArena’s Text-to-video leaderboard it ranks 42 of 48 with 1132±15 from 10,458 votes. On LMArena’s Image-to-video leaderboard it ranks 43 of 48 with 1170±10 from 27,054 votes. License: Apache 2.0.
Key figures
- Developer
- Alibaba
- License
- Apache 2.0
Not yet available: Released (per AA), AA Elo
Who it is for (from the data)
- When quality is not the top priority: #42 of 48 on Text-to-video, in the bottom half; if quality matters most, check higher-ranked models first.
- Both text- and image-to-video: it is ranked on both boards.
- Self-hosting or on-premise use: LMArena lists its license as Apache 2.0.
- Existing Alibaba users: this vendor has 4 models on Text-to-video.
Neighbours on Text-to-video
| # | Model | Score | Votes | AA Elo | License | Δ |
|---|---|---|---|---|---|---|
| 39 |  Veo 2 Google | 1164 | 6,531 | – | Proprietary | +32 |
| 40 |  Kling V2.1 Master Kling (Kuaishou) | 1163 | 14,104 | – | Proprietary | +31 |
| 41 | LLTX 2 19B Lightricks | 1154 | 75,596 | – | ltx-2-community-license-agreement | +22 |
| 42 | Wan V2.2 A14B Alibaba | 1132 | 10,458 | – | Apache 2.0 | |
| 43 |  Seedance V1 Lite ByteDance | 1113 | 16,253 | – | Proprietary | -19 |
| 44 | KKandinsky 5.0 T2V Lite Kandinsky | 1113 | 1,474 | – | MIT | -19 |
| 45 |  Sora OpenAI | 1069 | 4,082 | – | Proprietary | -63 |
Alternatives · More from Alibaba
| # | Model | Score | Votes | AA Elo | License |
|---|---|---|---|---|---|
| 6 | Wan 3.0 Alibaba | 1476 | 2,598 | 1135 | Proprietary |
| 21 | Wan 2.6 T2V Alibaba | 1327 | 54,050 | – | Proprietary |
| 25 | Wan 2.5 T2V Preview Alibaba | 1245 | 36,378 | – | Proprietary |
Alternatives · Top open-weight models
| # | Model | Score | Votes | AA Elo | License |
|---|---|---|---|---|---|
| 8 |  MiniMax H3 MiniMax | 1460 | 11,417 | 1122 | minimax-h3-community-license-agreement |
| 37 | KKandinsky 5.0 T2V Pro Kandinsky | 1175 | 2,019 | – | MIT |
| 38 |  Hunyuan Video 1.5 Tencent | 1169 | 4,292 | – | tencent-hunyuan-community |
| 41 | LLTX 2 19B Lightricks | 1154 | 75,596 | – | ltx-2-community-license-agreement |
| 44 | KKandinsky 5.0 T2V Lite Kandinsky | 1113 | 1,474 | – | MIT |
How to read the scores
- LMArena score: people blind-pick the better of two anonymous videos for the same prompt, and the votes are fitted into an Elo-style rating; "±" is the 95% confidence interval.
- Text-to-video and image-to-video are separate boards, so scores are not comparable across them; AA Elo comes from Artificial Analysis on a different scale.
- If the gap between two models is smaller than their combined intervals, the order is not statistically reliable; treat them as the same tier. More votes mean narrower intervals.
FAQ
Where does Wan V2.2 A14B rank among AI video models?
Text-to-video rank 42 (1132); Image-to-video rank 43 (1170) (LMArena, data as of Oct 26, 2026).
Is Wan V2.2 A14B open-weight?
LMArena lists its license as Apache 2.0 (not proprietary); check the license text for commercial-use terms.
Can Wan V2.2 A14B turn an image into video?
Who makes Wan V2.2 A14B?
According to LMArena, Wan V2.2 A14B is made by Alibaba.
How reliable is Wan V2.2 A14B's score?
The scores are based on 10,458 votes on Text-to-video (95% CI ±15); 27,054 votes on Image-to-video (95% CI ±10). More votes and narrower intervals mean a more stable rank.
How far is Wan V2.2 A14B from #1 on Text-to-video?
#1 on Text-to-video is Gemini Omni 1.1 Flash (1516); Wan V2.2 A14B scores 1132, 384 points behind.
Sources
LMArena Text-to-video data published on Sep 22, 2026.
LMArena Image-to-video data published on Sep 22, 2026.
17NAS syncs the upstream leaderboards daily; this page's data was synced on Oct 26, 2026.
Price, clip length, resolution and speed have no reliable public data yet and are omitted; all values come from the snapshot, blanks show –.