List your company

Agentic UI Interaction on GUIRILLA-TASK agentic

12.5Input Success RateQwen 2.5 VL 3B
1.36164.25337.14510.0367Oct 16, 2025

Evaluation results

MethodLinks
Qwen 2.5 VL 3BModel Size=3B, Base Model=Qwen 2.5 VL2025.1012.542.9540.77
Claude Computer Use2025.108.9365.5961.53
OpenAI Computer Use2025.108.0468.7564.41
OS-Atlas-Pro-7BModel Size=7B2025.107.1462.8458.85
UI TARS 2BModel Size=2B2025.107.1450.2447.16
CogAgent 9BModel Size=9B2025.103.5715.8314.95
Qwen 2.5 VL 7BModel Size=7B, Base Model=Qwen 2.5 VL2025.102.6839.1636.55
UI TARS 1.5 7BModel Size=7B, Version=1.52025.101.7954.6550.86