Benchmark
Arena ELO Video Edit
People compare model answers and choose which they prefer. Higher scores are better.
All human preference benchmarksScores from LMArena data.
- Models measured
- 12
- Scores recorded
- 12
- Sources
- 1
- IQ weight
- 1.36
Score distribution
- 1,326.8
- Mean
- 1,368
- Median
- 82.2
- Std dev
- 1,189.7
- 10th percentile
- 1,418.8
- 90th percentile
- 1,181.6
- Min
This benchmark has a weight of 1.36 for video-generation models, measured over 10 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Wan 3.0· LMArena data | 1,423.7 |
| 2 | Dreamina Seedance 2.5720p· LMArena data | 1,418.8 |
| 3 | Gemini Omni 1.2 Flash· LMArena data | 1,395.6 |
| 4 | Gemini Omni Flash Preview· LMArena data | 1,380.5 |
| 5 | MiniMax H3· LMArena data | 1,378.4 |
| 6 | Dreamina Seedance 2.0720p· LMArena data | 1,368 |
| 7 | SkyReels V4· LMArena data | 1,363.5 |
| 8 | HappyHorse 1.0· LMArena data | 1,305.7 |
| 9 | Kling O3 Pro· LMArena data | 1,265.7 |
| 10 | Grok Imagine Video· LMArena data | 1,249.8 |
| 11 | Kling O1 Pro· LMArena data | 1,189.7 |
| 12 | Runway Gen-4 Aleph· LMArena data | 1,181.6 |
Data credits: LMArena, CC BY 4.0 (licence)