List your company

Mobile Agent Decision-making on AndroidWorld (Evaluation set 116 templates)

62.9Average Success Rate (SR)MobileUse-72B
21.40432.17742.9553.723Mar 8, 2026

Evaluation results

MethodLinks
MobileUse-72BAPI-Based=false, Open-Source=true, Reproducible=true, Model Scale Category=32B/72B Models2026.0362.9
Agent S2API-Based=true, Open-Source=false, Reproducible=false, Model Scale Category=Proprietary model2026.0354.3
Ours-7BAPI-Based=false, Open-Source=true, Reproducible=true, Curriculum Learning=true, Model Scale Category=2B/7B Models2026.0349.1
UI-TARS-72B-SFTAPI-Based=false, Open-Source=true, Reproducible=true, Model Scale Category=32B/72B Models2026.0346.6
Ours-7B w/o curriculum learningAPI-Based=false, Open-Source=true, Reproducible=true, Curriculum Learning=false, Model Scale Category=2B/7B Models2026.0345.1
Aria-UI+GPT-4oAPI-Based=true, Open-Source=true, Reproducible=true, Model Scale Category=Proprietary model2026.0344.8
MobileGUI-32BAPI-Based=false, Open-Source=false, Reproducible=false, Model Scale Category=32B/72B Models2026.0344.8
UGround+GPT-4oAPI-Based=true, Open-Source=true, Reproducible=true, Model Scale Category=Proprietary model2026.0344
AppVLM-3BAPI-Based=false, Open-Source=false, Reproducible=false, Model Scale Category=2B/7B Models2026.0337.8
Qwen2.5-VL-72BAPI-Based=false, Open-Source=true, Reproducible=true, Model Scale Category=32B/72B Models2026.0335
GPT-4oAPI-Based=true, Open-Source=false, Reproducible=true, Model Scale Category=Proprietary model2026.0334.5
Qwen2.5-VL-32BAPI-Based=false, Open-Source=true, Reproducible=true, Model Scale Category=32B/72B Models2026.0331.5
MobileGUI-7BAPI-Based=false, Open-Source=false, Reproducible=false, Model Scale Category=2B/7B Models2026.0330
Claude Computer UseAPI-Based=true, Open-Source=false, Reproducible=true, Model Scale Category=Proprietary model2026.0327.9
AGUVIS-72BAPI-Based=false, Open-Source=false, Reproducible=false, Model Scale Category=32B/72B Models2026.0326.1
UI-TARS-7B-SFTAPI-Based=false, Open-Source=true, Reproducible=true, Model Scale Category=2B/7B Models2026.0323