Vidu Q3 Pro
LMArena ID: vidu-q3-pro
Shengshu (Vidu)Proprietary
Vidu Q3 Pro is an AI video model from Shengshu (Vidu). It is not on LMArena’s Text-to-video leaderboard yet. On LMArena’s Image-to-video leaderboard it ranks 18 of 48 with 1363±9 from 36,679 votes. License: Proprietary.
Key figures
- Developer
- Shengshu (Vidu)
- License
- Proprietary
- Released (per AA)
- Jan 2026
Not yet available: LMArena · Text-to-video
Who it is for (from the data)
- Solid quality with room to choose: #18 of 48 on Image-to-video, in the top half.
- Mainly image-to-video: no text-to-video results yet.
- Use via Shengshu (Vidu)'s service or API: LMArena lists it as proprietary.
- Existing Shengshu (Vidu) users: this vendor has 3 models on Image-to-video.
Neighbours on Image-to-video
| # | Model | Score | Votes | AA Elo | License | Δ |
|---|---|---|---|---|---|---|
| 15 |  Veo 3.1 Fast Audio Google | 1385 | 99,804 | – | Proprietary | +22 |
| 16 |  Grok Imagine Video 480p xAI | 1385 | 19,429 | – | Proprietary | +22 |
| 17 | Veo 3.1 Fast Audio 1080p Google | 1372 | 54,380 | – | Proprietary | +9 |
| 18 | SVidu Q3 Pro Shengshu (Vidu) | 1363 | 36,679 | 1290 | Proprietary | |
| 19 |  Kling V3 Pro Kling (Kuaishou) | 1354 | 206,221 | – | Proprietary | -9 |
| 20 | Veo 3 Audio Google | 1331 | 32,367 | – | Proprietary | -32 |
| 21 | Veo 3 Fast Audio Google | 1326 | 41,194 | – | Proprietary | -37 |
Alternatives · More from Shengshu (Vidu)
| # | Model | Score | Votes | AA Elo | License |
|---|---|---|---|---|---|
| 33 | SVidu Q2 Turbo Shengshu (Vidu) | 1244 | 2,509 | 1236 | Proprietary |
| 39 | SVidu Q2 Pro Shengshu (Vidu) | 1223 | 2,614 | 1233 | Proprietary |
Alternatives · Top open-weight models
| # | Model | Score | Votes | AA Elo | License |
|---|---|---|---|---|---|
| 1 |  MiniMax H3 MiniMax | 1495 | 57,112 | 1356 | minimax-h3-community-license-agreement |
| 40 |  Hunyuan Video 1.5 Tencent | 1198 | 5,462 | 1134 | tencent-hunyuan-community |
| 43 |  Wan V2.2 A14B Alibaba | 1170 | 27,054 | – | Apache 2.0 |
| 45 | LLTX 2 19B Lightricks | 1159 | 262,336 | – | ltx-2-community-license-agreement |
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 Vidu Q3 Pro rank among AI video models?
Image-to-video rank 18 (1363) (LMArena, data as of Oct 26, 2026).
Is Vidu Q3 Pro open-weight?
No. LMArena lists it as Proprietary; it is available only through Shengshu (Vidu)’s products or API.
Who makes Vidu Q3 Pro?
According to LMArena, Vidu Q3 Pro is made by Shengshu (Vidu).
How reliable is Vidu Q3 Pro's score?
The scores are based on 36,679 votes on Image-to-video (95% CI ±9). More votes and narrower intervals mean a more stable rank.
How far is Vidu Q3 Pro from #1 on Image-to-video?
#1 on Image-to-video is MiniMax H3 (1495); Vidu Q3 Pro scores 1363, 132 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 –.