VideoVIBE - Visual Hierarchy: leaderboard
Metric: Failure-diagnosis accuracy (%; questions of the Visual Hierarchy subdimension of Visual and Motion Fidelity; zero-shot single-choice diagnosis from the interaction video and the page source code (Video+HTML), about 1.7K questions built from 6,338 verified failures of one-shot generated web applications recorded under human operation; free-form answers mapped deterministically to an option). Source: arxiv.org. Saturation forecast: Around 2034. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 8B (Thinking) | 51.11 |
| 2 | Gemini 2.5 Flash | 43.11 |
| 3 | Gemini 3 Flash | 40 |
| 4 | Gemini 3.1 Pro (Preview) | 39.11 |
| 5 | Qwen 3 VL 8B Instruct | 39.11 |
| 6 | Qwen 3 VL 30B A3B (Thinking) | 39.11 |
| 7 | Qwen 3.5 35B A3B | 36.89 |
| 8 | GLM-4.6V | 36.89 |
| 9 | MiMo-V2.5 | 36.44 |
| 10 | Qwen 3 VL 30B A3B Instruct | 31.11 |
| 11 | Gemini 3.1 Flash Lite | 30.67 |
Interactive version: theaggregate.ai/benchmark?slug=videovibe-visual-hierarchy · How It Works · Data refreshed daily, snapshot 2026-09-29.