Veo 3 Audio
LMArena ID: veo-3-audio
GoogleProprietary
Veo 3 Audio is an AI video model from Google. On LMArena’s Text-to-video leaderboard it ranks 19 of 48 with 1340±13 from 19,002 votes. On LMArena’s Image-to-video leaderboard it ranks 20 of 48 with 1331±12 from 32,367 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: #19 of 48 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 11 models on Text-to-video.
Neighbours on Text-to-video
| # | Model | Score | Votes | AA Elo | License | Δ |
|---|---|---|---|---|---|---|
| 16 | Veo 3 Fast Audio Google | 1348 | 25,258 | – | Proprietary | +8 |
| 17 |  Sora 2 OpenAI | 1343 | 71,947 | – | Proprietary | +3 |
| 18 |  Grok Imagine Video 720p xAI | 1342 | 165,462 | – | Proprietary | +2 |
| 19 | Veo 3 Audio Google | 1340 | 19,002 | – | Proprietary | |
| 20 | WWan 2.7 T2V Wan | 1337 | 27,626 | – | Proprietary | -3 |
| 21 |  Wan 2.6 T2V Alibaba | 1327 | 54,050 | – | Proprietary | -13 |
| 22 |  Seedance V1.5 Pro ByteDance | 1256 | 76,171 | – | Proprietary | -84 |
Alternatives · More from Google
| # | Model | Score | Votes | AA Elo | License |
|---|---|---|---|---|---|
| 1 | Gemini Omni 1.1 Flash Google | 1516 | 1,784 | 1069 | Proprietary |
| 2 | Gemini Omni Flash Google | 1513 | 26,576 | – | Proprietary |
| 12 | Veo 3.1 Audio Google | 1364 | 13,741 | – | Proprietary |
| 13 | Veo 3.1 Audio 1080p Google | 1362 | 25,076 | – | Proprietary |
| 14 | Veo 3.1 Fast Audio Google | 1362 | 39,484 | – | 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 |
| 42 | Wan V2.2 A14B Alibaba | 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 Audio rank among AI video models?
Text-to-video rank 19 (1340); Image-to-video rank 20 (1331) (LMArena, data as of Oct 26, 2026).
Is Veo 3 Audio open-weight?
No. LMArena lists it as Proprietary; it is available only through Google’s products or API.
Can Veo 3 Audio turn an image into video?
Who makes Veo 3 Audio?
According to LMArena, Veo 3 Audio is made by Google.
How reliable is Veo 3 Audio's score?
The scores are based on 19,002 votes on Text-to-video (95% CI ±13); 32,367 votes on Image-to-video (95% CI ±12). More votes and narrower intervals mean a more stable rank.
How far is Veo 3 Audio from #1 on Text-to-video?
#1 on Text-to-video is Gemini Omni 1.1 Flash (1516); Veo 3 Audio scores 1340, 176 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 –.