Best video generator
Text-to-video, same method: two clips, a human picks one.
Right now
Gemini Omni 1.1 Flash from Google currently ranks first for making video from text, ahead of Gemini Omni Flash from Google. The ranking comes from LMArena and was last published 2026-08-27.
- Leader
- Gemini Omni 1.1 Flash
- Made by
- Score
- 1515
- Source
- LMArena
Full ranking
| Rank# | Model | Made by | Arena score | Votes |
|---|---|---|---|---|
| 1 | Gemini Omni 1.1 Flash | 1,515 | 1,762 | |
| 2 | Gemini Omni Flash | 1,512 | 19,830 | |
| 3 | Flux 3 Video | Bfl | 1,495 | 1,287 |
| 4 | Dreamina Seedance 2.0 720p | ByteDance | 1,479 | 51,266 |
| 5 | Dreamina Seedance 2.5 720p | ByteDance | 1,476 | 2,121 |
| 6 | Minimax H3 Open | MiniMax | 1,460 | 5,813 |
| 7 | Muse Video | Meta | 1,457 | 2,178 |
| 8 | Happyhorse 1.0 | Aorizon | 1,428 | 22,112 |
| 9 | Sora 2 Pro | OpenAI | 1,365 | 48,782 |
| 10 | Veo 3.1 Audio | 1,364 | 13,705 | |
| 11 | Veo 3.1 Audio 1080p | 1,363 | 24,972 | |
| 12 | Veo 3.1 Fast Audio | 1,361 | 39,371 | |
| 13 | Veo 3.1 Fast Audio 1080p | 1,358 | 25,768 | |
| 14 | Veo 3 Fast Audio | 1,347 | 25,169 | |
| 15 | Wan2.7 T2v | Wan | 1,344 | 20,882 |
| 16 | Grok Imagine Video 720p | xAI | 1,344 | 157,732 |
| 17 | Sora 2 | OpenAI | 1,341 | 65,433 |
| 18 | Veo 3 Audio | 1,340 | 18,941 | |
| 19 | Wan2.6 T2v | Alibaba | 1,329 | 47,267 |
| 20 | Seedance V1.5 Pro | ByteDance | 1,256 | 75,890 |
| 21 | Veo 3 | 1,253 | 14,951 | |
| 22 | Veo 3 Fast | 1,248 | 15,225 | |
| 23 | Wan2.5 T2v Preview | Alibaba | 1,247 | 30,497 |
| 24 | Pixverse V5.6 | Unknown | 1,240 | 32,296 |
| 25 | Runway Gen 4.5 | Runway | 1,224 | 41,583 |
Other leaderboards
- General questions, writing, reasoning Best overall chat model
- Writing and fixing code Best model for coding
- Multi-step work with tools Best agent model
- Reading screenshots, charts, scans Best model for images and documents
- Answers grounded in live sources Best model for search
- Making pictures from text Best image generator
- Cost per million tokens Cheapest capable models