GUI Agent Evaluation on Industrial e-commerce dataset
95.8AccuracyGUIDE
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| GUIDE2026.04 | 95.8 | 95 | 93.62 | 94.31 | |
| WebJudge2026.04 | 90.45 | 84.04 | 91.59 | 87.66 | |
| Autonomous Eval2026.04 | 84.44 | 77.93 | 80.87 | 79.37 | |
| Plan&Solve-like2026.04 | 82.94 | 72.91 | 85.8 | 78.83 | |
| AgentTrek2026.04 | 65.02 | 51.42 | 100 | 67.91 |