AutoGUI-v2 - Region Grounding (Description): leaderboard

AutoGUI-v2 (2026) tests functionality understanding of GUI regions and elements on web, desktop and mobile screenshots. This board asks the model to locate a functional region from its layout description; a prediction counts when its point falls inside the ground-truth box. Accuracy in percent; higher is better.

Metric: Region grounding by layout description on the same regions, grounding center accuracy (%): the predicted point falls inside the ground-truth box; native resolution, the authors' tuned prompts; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GLM-4.5V93.7#754
2Qwen 3 VL 32B Instruct92.3#606
3UGround-V1-7B88.5
4Qwen 3 VL 8B Instruct87.3#1029
5uitars-1.5-7B78.3#7905
6Gemini 2.5 Pro77.8#276
7OS-Atlas-Base-7B72.4
8Claude Sonnet 4.550.7#261
9O349.2#237
10Step-347.5#734
11GPT-536.7#178

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-grounding-description · How It Works · Data refreshed daily, snapshot 2026-11-21.