List your company

GUI Grounding on UI-Vision Spatial

14.1Top-1 AccuracyOurs (Qwen3-VL-8B)
-0.2523.4747.210.926Apr 23, 2026

Evaluation results

MethodLinks
Ours (Qwen3-VL-8B)Model Category=Ours2026.0414.1
Qwen3-VL-8BModel Category=General Open-source Models2026.0410.8
GUI-SpotlightModel Category=GUI-specific Models2026.049.1
Qwen3-VL-4BModel Category=General Open-source Models2026.048.8
Claude-3.7 SonnetModel Category=Closed-Source Models2026.047.6
Ours (UI-Tars1.5)Model Category=Ours2026.047.4
UI-TARS-1.5-7BModel Category=GUI-specific Models2026.046.6
UGround-V1-7BModel Category=GUI-specific Models2026.046.3
Aguvis-7BModel Category=GUI-specific Models2026.045.1
OS-Atlas-Base-7BModel Category=GUI-specific Models2026.043.7
Qwen3-VL-2BModel Category=General Open-source Models2026.042.1
GPT-4oModel Category=Closed-Source Models2026.041
Qwen2.5-VL-7BModel Category=General Open-source Models2026.040.5
Qwen2.5-VL-3BModel Category=General Open-source Models2026.040.3