Arena Video Edit
- What does it measure?
- Tests, through user preference votes, how well models edit a video according to an instruction.
- Who evaluates it, and how?
- A user provides a video and an edit instruction; two anonymous video-editing models produce results and the user votes for the one they prefer. The votes are combined into a score on the Elo scale, a rating built from head-to-head results.
- Reading the score
- Scores are Elo ratings from head-to-head human votes. Higher is better. It is a small board with few models.
- Related benchmarks
- Arena Document|Arena Image-to-Video|Arena Search|Arena Text Factuality
Top score1419
Models tested6
Scoring basisHigher is betterImage-input models only
Last updated2026.11.10
Model release date
Which AI makes the images people prefer most?Arena T2I
GPT Image 2.5 Sunburst🥇
GPT Image 2.5 Sunburst🥇Arena T2I
GPT Image 2.5 Sunburst🥇Which AI edits images the way people prefer most?Arena Image Edit
GPT Image 2.5 Sunburst🥇
GPT Image 2.5 Sunburst🥇Arena Image Edit
GPT Image 2.5 Sunburst🥇Which AI do people prefer most for turning photos into videos?Arena Image-to-Video
Gemini Omni 1.2 Flash🥇
Gemini Omni 1.2 Flash🥇Arena Image-to-Video
Gemini Omni 1.2 Flash🥇
Which AI edits videos the way people prefer most?
Arena Video Edit
- 🥇ByteDanceSeedance 2.51419
- 🥈GoogleGemini Omni 1.2 Flash1396
- 🥉MiniMaxH31378
- #4ByteDanceSeedance 2.01368
- #5AlibabaHappyHorse 1.01306
- #6SpaceXSIGrok Imagine Video1250
Half of models ≤ 1373