VEFX-Bench - Rendering Quality: 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 rendering-quality score on a 1 to 4 scale; higher is better.
Metric: Rendering-quality score 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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kling 3.0 Omni | 3.59 | |
| 2 | Kling o1 | 3.53 | |
| 3 | Seedance 2.0 | 3.42 | |
| 4 | Luma ray 3 | 3.4 | |
| 5 | Grok Imagine | 3.35 | |
| 6 | Runway Gen-4.5 | 3.32 | |
| 7 | Wan2.6 | 3.32 | |
| 8 | UniVideo | 3.27 | |
| 9 | VACE (VEFX-Bench checkpoint unspecified) | 3.17 | |
| 10 | Luma ray 2 | 2.53 |
Interactive version: theaggregate.ai/benchmark?slug=vefx-bench-rendering-quality · How It Works · Data refreshed daily, snapshot 2026-11-21.