Share your thoughts, 1 month free Claude Pro on usSee more

GUI Automation on MiniWob++

77.2Success Rate

LAMO-3B

Updated 3d ago

Evaluation Results

Method	Links
LAMO-3B 2026.04		77.2
Gemini-2.5-pro 2026.04		71
Aguvis-72B 2026.04		66
GPT-4o (SoM) 2026.04		62
UI-Copilot-7B 2026.04		61.2
UI-S1-7B 2026.04		60.9
LAMO-3B 2026.04		60.9
UI-S1-7B 2026.04		60.9
UI-TARS-7B 2026.04		58.7
UI-TARS-7B 2026.04		58.7
Qwen2.5-VL-7B 2026.04		54
Qwen2.5VL-7B 2026.04		54
LAMO-3B 2026.04		50
UI-R1-7B 2026.04		45.2
AgentCPM-GUI-8B 2026.04		37.8
AgentCPM-GUI-8B 2026.04		37.8
OS-Atlas-7B 2026.04		35.2
OS-Atlas-7B 2026.04		35.2
Qwen2.5-VL-3B 2026.04		34.6
ShowUI-2B 2026.04		27.1
UI-R1-3B 2026.04		26.1
UI-Copilot-3B 2026.04		25.9
Qwen2.5VL-3B 2026.04		24.1
Qwen2VL-2B 2026.04		20.8
OS-Genesis-7B 2026.04		19.8