List your company

GUI Automation on AITW Gen

19.5PGUI-S1-7B
0.785.6410.515.36Apr 7, 2026

Evaluation results

MethodLinks
UI-S1-7BCategory=Open-src, Scale=7B/8B2026.0419.54.6
Gemini-3-flashCategory=Closed-source2026.0417.84.5
UI-TARS-7BCategory=Open-src, Scale=7B/8B2026.0416.85.9
VeriGUI-7BCategory=Ours, Scale=7B2026.0415.55.5
OS-Atlas-7BCategory=Open-src, Scale=7B/8B2026.0412.33.4
AgentCPM-GUI-8BCategory=Open-src, Scale=7B/8B2026.04123.4
Qwen2.5-VL-7BCategory=Open-src, Scale=7B/8B2026.0411.73
GPT-5.1Category=Closed-source2026.0410.42.5
UI-R1-3BCategory=Open-src, Scale=3B2026.048.82.4
VeriGUI-3BCategory=Ours, Scale=3B2026.047.42.6
OS-Genesis-7BCategory=Open-src, Scale=7B/8B2026.046.52.2
Qwen2.5-VL-3BCategory=Open-src, Scale=3B2026.041.50.1