AutoGUI-v2 - Region Captioning: leaderboard
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: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 88.1 |
| 2 | GLM-4.5V | 86.8 |
| 3 | Gemini 2.5 Pro | 86.2 |
| 4 | Claude Sonnet 4.5 | 84 |
| 5 | O3 | 84 |
| 6 | Qwen 3 VL 32B Instruct | 80.1 |
| 7 | Qwen 3 VL 8B Instruct | 66.3 |
Interactive version: theaggregate.ai/benchmark?slug=autogui-v2-region-captioning · How It Works · Data refreshed daily, snapshot 2026-10-07.