VEBench: leaderboard
VEBench (2026) tests large multimodal models on real-world video editing tasks. The overall score is the mean of Technique Recognition accuracy and Footage Selection accuracy with subtitles, in percent; higher is better.
Metric: Overall score (%): mean of Technique Recognition accuracy and Footage Selection accuracy with subtitles; higher is better. Source: arxiv.org. Saturation forecast: Around February 2028. 9 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 39.55 | #280 |
| 2 | Qwen 3 VL 32B Instruct | 34.36 | #607 |
| 3 | GPT-4o | 33.29 | #754 |
| 4 | Qwen 3 VL 8B Instruct | 32.39 | #1043 |
| 5 | Qwen 3 VL 4B Instruct | 30.2 | #1348 |
| 6 | InternVL3-14B | 29.12 | #1227 |
| 7 | Qwen 3 VL 30B A3B Instruct | 28.84 | #903 |
| 8 | Qwen 2.5 VL 7B Instruct | 28.74 | #1919 |
| 9 | InternVL3-8B | 27.99 | #1795 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=vebench · How It Works · Data refreshed daily, snapshot 2026-11-22.