List your company

GUI Grounding on UI-Vision Functional

34.5Top-1 AccuracyOurs (Qwen3-VL-8B)
-1.1728.08917.3526.611Apr 23, 2026

Evaluation results

MethodLinks
Ours (Qwen3-VL-8B)Model Category=Ours2026.0434.5
Qwen3-VL-8BModel Category=General Open-source Models2026.0430.6
GUI-SpotlightModel Category=GUI-specific Models2026.0430.2
Qwen3-VL-4BModel Category=General Open-source Models2026.0426.5
UI-TARS-1.5-7BModel Category=GUI-specific Models2026.0425.1
Ours (UI-Tars1.5)Model Category=Ours2026.0422.9
Aguvis-7BModel Category=GUI-specific Models2026.0418.3
UGround-V1-7BModel Category=GUI-specific Models2026.0417.1
OS-Atlas-Base-7BModel Category=GUI-specific Models2026.0411.2
Qwen3-VL-2BModel Category=General Open-source Models2026.049.3
Claude-3.7 SonnetModel Category=Closed-Source Models2026.047.7
GPT-4oModel Category=Closed-Source Models2026.041.5
Qwen2.5-VL-7BModel Category=General Open-source Models2026.040.8
Qwen2.5-VL-3BModel Category=General Open-source Models2026.040.2