List your company

GUI Automation on MiniWob++

77.2Success RateLAMO-3B
17.50433.00248.563.998Apr 15, 2026

Evaluation results

MethodLinks
LAMO-3BReasoning Mode=Policy Executor Mode, Planner=Gemini-2.5-pro2026.0477.2
Gemini-2.5-pro2026.0471
Aguvis-72B2026.0466
GPT-4o (SoM)2026.0462
UI-Copilot-7B2026.0461.2
UI-S1-7B2026.0460.9
LAMO-3BReasoning Mode=Multi-Agent System2026.0460.9
UI-S1-7B2026.0460.9
UI-TARS-7B2026.0458.7
UI-TARS-7B2026.0458.7
Qwen2.5-VL-7B2026.0454
Qwen2.5VL-7B2026.0454
LAMO-3BReasoning Mode=End2End Reasoning2026.0450
UI-R1-7B2026.0445.2
AgentCPM-GUI-8B2026.0437.8
AgentCPM-GUI-8B2026.0437.8
OS-Atlas-7B2026.0435.2
OS-Atlas-7B2026.0435.2
Qwen2.5-VL-3B2026.0434.6
ShowUI-2B2026.0427.1
UI-R1-3B2026.0426.1
UI-Copilot-3B2026.0425.9
Qwen2.5VL-3B2026.0424.1
Qwen2VL-2B2026.0420.8
OS-Genesis-7B2026.0419.8