Veo 2 vs Ray2
Preferred for text to video: Veo 2 · Preferred for image to video: Veo 2 · Newest: Ray2. Quality scores are blind human-preference votes; specs and prices come from each lab’s listings.
Where they differ
Quality is the arena score from blind, side-by-side human votes. Price, length and resolution come from each lab’s own listings.
- Preferred for text to videoVeo 2Veo 2 1,164 (#39) · Ray2 1,065 (#46) — blind human votes
- Preferred for image to videoVeo 2Veo 2 1,166 (#44) · Ray2 1,108 (#46) — blind human votes
- NewestRay2Veo 2 Dec 2, 2024 · Ray2 Feb 20, 2025
- Widest inputsRay2Veo 2: Text prompts · Ray2: Text prompts, Reference images
- Native audioNo native audioGenerates an audio track with the video: Veo 2 no · Ray2 no
- Image to videoRay2Starts from an uploaded image: Veo 2 no · Ray2 yes
- Self-hostingNo open weightsBoth are available only through APIs and apps
- Most API hostsSame reachVeo 2: 1 · Ray2: 1
Every spec in one table
Dashes mean the data is not published.
| Specification | ||
|---|---|---|
| Quality (blind human votes) | ||
| Text to video arenaElo-style score · higher is better | 1,164 ±16#39 of 48 · 6,531 votes (best) | 1,065 ±17#46 of 48 · 5,250 votes |
| Image to video arenaElo-style score · higher is better | 1,166 ±16#44 of 48 · 10,303 votes (best) | 1,108 ±16#46 of 48 · 9,521 votes |
| Output | ||
| Produces | Video | Video |
| Inputs | ||
| Text prompts | Yes | Yes |
| Start image (image to video) | No | Yes |
| Video input | No | No |
| Audio input | No | No |
| Access | ||
| Weights | Proprietary | Proprietary |
| API hosts | 1 | 1 |
| Released | Dec 2, 2024 | Feb 20, 2025 |
Which should you choose?
Which is better, Veo 2 or Ray2?
For text to video, voters prefer Veo 2 (Veo 2 1,164 (#39) · Ray2 1,065 (#46)). For image to video, voters prefer Veo 2 (Veo 2 1,166 (#44) · Ray2 1,108 (#46)). Arena scores come from blind, side-by-side human votes on the same prompts; when the gap is inside both models’ error margins we call it a tie. Test your own prompts before you commit.
What is the difference between Veo 2 and Ray2?
Veo 2 is a video model from Google (Dec 2, 2024), taking text prompts and producing video. Ray2 is a video model from Luma AI (Feb 20, 2025), taking text prompts and reference images and producing video.
Which is newer?
Veo 2 Dec 2, 2024; Ray2 Feb 20, 2025.
Which generates video with sound?
Generates an audio track with the video: Veo 2 no; Ray2 no.
Can I run any of these on my own hardware?
No open weights. Both are available only through APIs and apps.