VEFX-Bench - Edit Exclusivity: leaderboard

VEFX-Bench (2026) compares instruction-guided video editing systems on curated source videos and editing prompts, scoring each edit with a reward model trained on human-annotated edits. This board is the coverage-adjusted edit-exclusivity score on a 1 to 4 scale, which rewards leaving unrequested content unchanged; higher is better.

Metric: Edit-exclusivity score (unrequested changes avoided) as a coverage-adjusted model-level estimate (inverse-propensity-weighted mixed-effects) on the 1-4 rubric scale over the 300 curated VEFX-Bench source-video and instruction pairs, each system's edited video scored by the authors' VEFX-Reward-32B evaluator from soft expected predictions; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 10 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Grok Imagine3.38
2UniVideo3.09
3Seedance 2.03.09
4Kling 3.0 Omni3.04
5Kling o12.98
6Runway Gen-4.52.92
7Luma ray 32.71
8Wan2.62.45
9Luma ray 21.36
10VACE (VEFX-Bench checkpoint unspecified)1.18

Interactive version: theaggregate.ai/benchmark?slug=vefx-bench-edit-exclusivity · How It Works · Data refreshed daily, snapshot 2026-11-22.