List your company

Step success rate on AndroidControl (Cat-Unseen)

61.2Step Success Rate (SSR)T3A* (Qwen2.5-7B-Instruct-ASL)
25.3234.63543.9553.265Jun 21, 2025

Evaluation results

MethodLinks
T3A* (Qwen2.5-7B-Instruct-ASL)Type=Fine-Tuned, Agent=T3A*, Model=Qwen2.5-7B-Instruct-ASL (Ours), Input Modality=Text2025.0661.2
M3A (GPT-4o)Type=Prompt-Driven, Agent=M3A, Model=GPT-4o, Input Modality=Image + Text2025.0660.8
T3A* (Qwen2.5-7B-Instruct-SFT)Type=Fine-Tuned, Agent=T3A*, Model=Qwen2.5-7B-Instruct-SFT, Input Modality=Text2025.0659.7
T3A (GPT-4o)Type=Prompt-Driven, Agent=T3A, Model=GPT-4o, Input Modality=Text2025.0656.5
M3A (Gemini-2.5-Flash)Type=Prompt-Driven, Agent=M3A, Model=Gemini-2.5-Flash, Input Modality=Image + Text2025.0647.9
T3A* (Gemini-2.5-Flash)Type=Prompt-Driven, Agent=T3A*, Model=Gemini-2.5-Flash, Input Modality=Text2025.0644.7
T3A (Gemini-2.5-Flash)Type=Prompt-Driven, Agent=T3A, Model=Gemini-2.5-Flash, Input Modality=Text2025.0644.4
SeeAct (Gemini-2.5-Flash)Type=Prompt-Driven, Agent=SeeAct, Model=Gemini-2.5-Flash, Input Modality=Image + Text2025.0633.7
SeeAct (GPT-4o)Type=Prompt-Driven, Agent=SeeAct, Model=GPT-4o, Input Modality=Image + Text2025.0630.6
T3A* (Qwen2.5-7B-Instruct)Type=Prompt-Driven, Agent=T3A*, Model=Qwen2.5-7B-Instruct, Input Modality=Text2025.0626.7