AutoGUI-v2 - Region Captioning: leaderboard
AutoGUI-v2 (2026) tests functionality understanding of GUI regions and elements on web, desktop and mobile screenshots. This board asks which of several options states the function of a region, with easy and hard distractors. Accuracy in percent; higher is better.
Metric: Region functionality captioning on 447 tasks, multiple-choice accuracy (%) with easy and hard (same-group) distractors; the authors' tuned prompts; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 88.1 | #178 |
| 2 | GLM-4.5V | 86.8 | #754 |
| 3 | Gemini 2.5 Pro | 86.2 | #276 |
| 4 | Claude Sonnet 4.5 | 84 | #261 |
| 5 | O3 | 84 | #237 |
| 6 | Qwen 3 VL 32B Instruct | 80.1 | #606 |
| 7 | Qwen 3 VL 8B Instruct | 66.3 | #1029 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=autogui-v2-region-captioning · How It Works · Data refreshed daily, snapshot 2026-11-21.