Mobile Task Automation on AndroidWorld (test)
1Average Success RateMinitap
Evaluation Results
| Method | Links | ||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MinitapType=Agent2026.02 | 1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AGI-0Type=Agent, Closed-source=true2026.02 | 0.974 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| askui AndroidVisionAgentType=Agent2026.02 | 0.948 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DroidRunType=Agent2026.02 | 0.914 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Agent-ViscoType=Agent, Closed-source=true2026.02 | 0.888 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DroidRun(v0.3.9)+AppCardsModel=GPT-5, Screen Representation=Screenshot + A11y tree2026.01 | 0.888 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| gbox.aiType=Agent2026.02 | 0.862 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| mobile-useModel=Llama 4-scout, Gemini 2.5 pro, GPT-5 nano, Screen Representation=Screenshot + A11y tree2026.01 | 0.845 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-Voyager#Params=4B2026.03 | 0.81 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AutoGLM-MobileType=Model, Parameters=9B2026.02 | 0.802 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AutoGLM-MobileModel=AutoGLM-Mobile, Screen Representation=Screenshot + A11y tree2026.01 | 0.802 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HumanType=Human baseline2026.02 | 0.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Human#Params=-2026.03 | 0.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LX-GUIAgentModel=LX-GUIAgent, Screen Representation=Screenshot + A11y tree2026.01 | 0.793 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DroidRun(v0.3.9)Model=GPT-5, Gemini 2.5 Pro, Screen Representation=Screenshot + A11y tree2026.01 | 0.784 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-Venus-1.5-30B-A3B#Params=30B2026.03 | 0.776 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MAI-UIType=Model, Parameters=235B2026.02 | 0.767 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FinalRunType=Training free, Base Model=GPT-5, Input=Screenshot + A11y2026.02 | 0.767 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MAI-UI-235B-A22B#Params=235B2026.03 | 0.767 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| K2-AgentType=Ours, Base Model=Qwen2.5-VL (72B+7B), Input=Screenshot2026.02 | 0.761 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AutoGLM-MobileType=Learning based, Base Model=AutoGLM-Mobile, Input=Screenshot + A11y2026.02 | 0.758 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MobileUse-v2Model=Hammer-UI-32B, Screen Representation=Screenshot + A11y tree2026.01 | 0.75 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mobile-Agent-v3Model=GUI-Owl-32B, Screen Representation=Screenshot2026.01 | 0.733 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mobile-Agent-v3Type=Learning based, Base Model=Qwen-VL based, Input=Screenshot2026.02 | 0.733 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-TARS-2Type=Learning based, Base Model=Seed-thinking-1.6, Input=Screenshot2026.02 | 0.733 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MAI-UI-32B#Params=32B2026.03 | 0.733 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-Tars-2#Params=230B2026.03 | 0.733 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DroidRun(v0.3.9)+AppCardsModel=Gemini-2.5-Pro, Screen Representation=Screenshot + A11y tree2026.01 | 0.716 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GUI-Owl-1.5-8B-Thinking#Params=8B2026.03 | 0.716 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MAI-UIType=Model, Parameters=8B2026.02 | 0.707 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MAI-UI-8B#Params=8B2026.03 | 0.707 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Seed1.8#Params=-2026.03 | 0.707 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Gemini 2.5 ComputerType=Model, Closed-source=true2026.02 | 0.697 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Gemini-2.5-Pro#Params=-2026.03 | 0.697 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DroidRun(v0.3.3)+AppCardsModel=Gemini-2.5-Pro, Screen Representation=Screenshot + A11y tree2026.01 | 0.69 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Step-GUI-8B#Params=8B, Reference=Yan et al., 2025a2026.03 | 0.677 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Step-GUI-8B#Params=8B, Reference=Yan et al., 2025b2026.03 | 0.677 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| JT-GUIAgent-V2Model=JT-GUIAgent-V2, Screen Representation=Screenshot2026.01 | 0.672 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GUI-Owl-7BType=Model, Parameters=7B2026.02 | 0.664 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DMS-PA-LiteUniv.=true, Weights=true, Train.=true, Mem.=true, Model=Qwen2.5-VL-72B-Instruct2026.01 | 0.664 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GUI-Owl-7B#Params=7B2026.03 | 0.664 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-VenusType=Model, Parameters=72B2026.02 | 0.659 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-VenusUniv.=true, Weights=true, Train.=false, Mem.=false, Model=Qwen2-VL-72B-Instruct2026.01 | 0.659 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-VenusType=Learning based, Base Model=Qwen2.5-VL-72B, Input=Screenshot2026.02 | 0.659 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-Venus-72B#Params=72B2026.03 | 0.659 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-TARS 1.52025.05 | 0.642 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-Tars-1.5#Params=-2026.03 | 0.642 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Step-GUI-4B#Params=4B2026.03 | 0.639 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen3-VL-235B-A22B#Params=235B2026.03 | 0.637 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DroidRun(v0.3.3)Model=Gemini-2.5-Pro, Screen Representation=Screenshot + A11y tree2026.01 | 0.63 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DroidRunType=Training free, Base Model=Gemini-2.5-Pro, Input=Screenshot + A11y2026.02 | 0.63 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MobileUseUniv.=false, Weights=true, Train.=true, Mem.=true, Model=Qwen2.5-VL-72B-Instruct2026.01 | 0.629 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MobileUseType=Training free, Base Model=Qwen2.5-VL-72B, Input=Screenshot2026.02 | 0.629 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Seed 1.5-VL2025.05 | 0.621 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Seed1.5-VLType=Model, Parameters=20B2026.02 | 0.621 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Seed1.5-VLUniv.=true, Weights=true, Train.=true, Mem.=false, Model=Seed1.5-VL2026.01 | 0.621 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Seed1.5-VLType=Learning based, Base Model=Seed1.5-VL-72B, Input=Screenshot + A11y2026.02 | 0.621 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Seed1.5-VL#Params=-2026.03 | 0.621 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DroidRun(v0.3.9)+AppCardsModel=Grok-4-Fast, Screen Representation=Screenshot + A11y tree2026.01 | 0.603 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| JT-GUIAgent-V1Model=JT-GUIAgent-V1, Screen Representation=Screenshot2026.01 | 0.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| V-DroidUniv.=false, Weights=true, Train.=false, Mem.=true, Model=V-Droid2026.01 | 0.595 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| V-DroidModel=V-Droid (Llama-8B), Screen Representation=A11y tree2026.01 | 0.595 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen3-VL-32B#Params=32B2026.03 | 0.573 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DMS-PA-LiteUniv.=true, Weights=false, Train.=true, Mem.=true, Model=Seed1.6-VL2026.01 | 0.56 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Agent-S2Univ.=true, Weights=false, Train.=true, Mem.=true, Model=Claude-3.7-Sonnet2026.01 | 0.543 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Agent S2Model=Agent S2, Screen Representation=Screenshot2026.01 | 0.543 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Agent S2Type=Training free, Base Model=Claude-3.5-Sonnet, Input=Screenshot2026.02 | 0.543 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EchoTrail-GUIUniv.=false, Weights=false, Train.=true, Mem.=true, Model=GPT-4o2026.01 | 0.517 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DMS-PA-LiteUniv.=true, Weights=true, Train.=true, Mem.=true, Model=GLM-4.5V2026.01 | 0.504 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MAI-UI-2B#Params=2B2026.03 | 0.491 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-Venus-7B#Params=7B2026.03 | 0.491 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen3-VL-8B#Params=8B2026.03 | 0.476 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GUI-ExplorerModel=GPT-4o, Screen Representation=Screenshot + A11y tree2026.01 | 0.474 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ANDROIDGENBase Model=GPT-4o, Fine-tuned=false2025.04 | 0.468 | 1 | 0.125 | 1 | 0 | 0.667 | 0.667 | 0.375 | 0.5 | 1 | 0.357 | 0.167 | 0.333 | 0.455 | 0.5 | 0.933 | 0.571 | 0.167 | 0.5 | — | |
| AndroidGenUniv.=false, Weights=false, Train.=true, Mem.=true, Model=GPT-4o2026.01 | 0.468 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AndroidGenModel=GPT-4o, Screen Representation=A11y tree2026.01 | 0.468 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AndroidGenType=Training free, Base Model=GPT-o, Input=A11y Tree2026.02 | 0.468 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-TARSType=Model, Parameters=72B2026.02 | 0.466 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EchoTrail-GUIUniv.=false, Weights=true, Train.=true, Mem.=true, Model=Qwen2.5-VL-72B-Instruct2026.01 | 0.466 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-TARSUniv.=true, Weights=true, Train.=false, Mem.=false, Model=Qwen2-VL-72B-Instruct2026.01 | 0.466 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-TARSModel=UI-TARS, Screen Representation=Screenshot2026.01 | 0.466 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-TARSType=Learning based, Base Model=Qwen-2-VL-72B, Input=Screenshot2026.02 | 0.466 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UI-Tars-SFT-72B#Params=72B2026.03 | 0.466 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen3-VL-4B#Params=4B2026.03 | 0.453 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MobileGUI-RLType=Model, Parameters=32B2026.02 | 0.448 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Aria-UIType=Model2026.02 | 0.448 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Aria-UIUniv.=true, Weights=false, Train.=false, Mem.=false, Model=GPT-4o + Aria-UI2026.01 | 0.448 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Aria-UIModel=GPT-4o + Aria-UI, Screen Representation=Screenshot2026.01 | 0.448 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UGroundType=Model2026.02 | 0.44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UGroundUniv.=false, Weights=false, Train.=true, Mem.=false, Model=GPT-4o2026.01 | 0.44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DMS-PA-LiteUniv.=true, Weights=true, Train.=true, Mem.=true, Model=Qwen3-VL 30B-A3B-Instruct2026.01 | 0.44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PA-LiteUniv.=true, Weights=false, Train.=true, Mem.=false, Model=Seed1.6-VL2026.01 | 0.394 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1.3 | |
| PA-LiteUniv.=true, Weights=true, Train.=true, Mem.=false, Model=Qwen2.5-VL-72B-Instruct2026.01 | 0.392 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1.5 | |
| AguvisUniv.=true, Weights=false, Train.=false, Mem.=false, Model=GPT-4o + Aguvis2026.01 | 0.371 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen3-VL-2B#Params=2B2026.03 | 0.364 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ANDROIDGENBase Model=Llama-3-70B, Fine-tuned=true2025.04 | 0.353 | 1 | 0.063 | 1 | 0 | 0.667 | 0.333 | 0.333 | 0.5 | 0.5 | 0.286 | 0.167 | 0 | 0.4 | 0.25 | 0.7 | 0.667 | 0 | 0 | — | |
| PA-LiteUniv.=true, Weights=true, Train.=true, Mem.=false, Model=GLM-4.5V2026.01 | 0.352 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1.9 | |
| Qwen 2.5 VL 72BParameters=72B2025.05 | 0.35 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen2.5-VLUniv.=true, Weights=true, Train.=true, Mem.=false, Model=Qwen2.5-VL-72B-Instruct2026.01 | 0.35 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GPT-4oUniv.=true, Weights=false, Train.=true, Mem.=false, Model=GPT-4o2026.01 | 0.345 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |