Veo 3.1 (Audio)
GoogleProprietary
Veo 3.1 (Audio) is an AI video model from Google. On LMArena’s Text-to-video leaderboard it ranks 14 of 50 with 1363±14 from 13,819 votes. On LMArena’s Image-to-video leaderboard it ranks 15 of 50 with 1399±10 from 25,283 votes. License: Proprietary.
Key figures
- Developer
- License
- Proprietary
Not yet available: Released (per AA), AA Elo
Who it is for (from the data)
- Solid quality with room to choose: #14 of 50 on Text-to-video, in the top half.
- Both text- and image-to-video: it is ranked on both boards.
- Use via Google's service or API: LMArena lists it as proprietary.
- Existing Google users: this vendor has 12 models on Text-to-video.
Neighbours on Text-to-video
| # | Model | Score | Votes | AA Elo | License | Δ |
|---|---|---|---|---|---|---|
| 11 | 1457 | 28,943 | 1120 | minimax-h3-community-license-agreement | +94 | |
| 12 | AHappyHorse 1.0 Aorizon | 1428 | 23,006 | 1032 | Proprietary | +65 |
| 13 | 1367 | 56,208 | – | Proprietary | +4 | |
| 14 | 1363 | 13,819 | – | Proprietary | ||
| 15 | 1363 | 25,760 | – | Proprietary | +0 | |
| 16 | 1361 | 40,389 | – | Proprietary | -2 | |
| 17 | 1357 | 26,595 | – | Proprietary | -6 |
Alternatives · More from Google
| # | Model | Score | Votes | AA Elo | License |
|---|---|---|---|---|---|
| 1 | 1541 | 1,742 | – | Proprietary | |
| 2 | 1514 | 1,803 | 1069 | Proprietary | |
| 3 | 1509 | 46,396 | – | Proprietary | |
| 15 | 1363 | 25,760 | – | Proprietary | |
| 16 | 1361 | 40,389 | – | Proprietary |
Alternatives · Top open-weight models
| # | Model | Score | Votes | AA Elo | License |
|---|---|---|---|---|---|
| 11 | 1457 | 28,943 | 1120 | minimax-h3-community-license-agreement | |
| 39 | KKandinsky 5.0 Video Pro Kandinsky | 1176 | 2,026 | – | MIT |
| 40 | 1168 | 4,334 | – | tencent-hunyuan-community | |
| 43 | LLTX-2 19B | 1156 | 93,052 | – | ltx-2-community-license-agreement |
| 44 | 1132 | 10,458 | – | Apache 2.0 |
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 Veo 3.1 (Audio) rank among AI video models?
Text-to-video rank 14 (1363); Image-to-video rank 15 (1399) (LMArena, data as of Nov 7, 2026).
Is Veo 3.1 (Audio) open-weight?
No. LMArena lists it as Proprietary; it is available only through Google’s products or API.
Can Veo 3.1 (Audio) turn an image into video?
Who makes Veo 3.1 (Audio)?
According to LMArena, Veo 3.1 (Audio) is made by Google.
How reliable is Veo 3.1 (Audio)'s score?
The scores are based on 13,819 votes on Text-to-video (95% CI ±14); 25,283 votes on Image-to-video (95% CI ±10). More votes and narrower intervals mean a more stable rank.
How far is Veo 3.1 (Audio) from #1 on Text-to-video?
#1 on Text-to-video is Gemini Omni 1.2 Flash (1541); Veo 3.1 (Audio) scores 1363, 178 points behind.
Sources
LMArena Text-to-video data published on Nov 6, 2026.
LMArena Image-to-video data published on Nov 6, 2026.
17NAS syncs the upstream leaderboards daily; this page's data was synced on Nov 7, 2026.
Price, clip length, resolution and speed have no reliable public data yet and are omitted; all values come from the snapshot, blanks show –.