List your company

GUI Agent Evaluation on Industrial e-commerce dataset

95.8AccuracyGUIDE
63.788872.099480.4188.7206Apr 6, 2026

Evaluation results

MethodLinks
GUIDE2026.0495.89593.6294.31
WebJudge2026.0490.4584.0491.5987.66
Autonomous Eval2026.0484.4477.9380.8779.37
Plan&Solve-like2026.0482.9472.9185.878.83
AgentTrek2026.0465.0251.4210067.91