GUI Agent on GUI-Odyssey
90.74Type AccuracyLearn from GUI-Odyssey
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Learn from GUI-OdysseyBase Model=OS-Atlas-Pro-7B, Learning Strategy=Supervised Fine-Tuning, Training Source=GUI-Odyssey2026.01 | 90.74 | 76.06 | 462 | |
| CL from all threeBase Model=OS-Atlas-Pro-7B, Learning Strategy=Continual Learning, Training Source=AITZ, AndroidControl, GUI-Odyssey2026.01 | 90.69 | 75.79 | 444 | |
| Agent-DiceBase Model=OS-Atlas-Pro-7B, Learning Strategy=Geometric Consensus & Curvature Importance Weighting2026.01 | 89.27 | 72.28 | 210 | |
| Learn from AITZBase Model=OS-Atlas-Pro-7B, Learning Strategy=Supervised Fine-Tuning, Training Source=AITZ2026.01 | 83.33 | 60.19 | 54 | |
| Learn from AndroidControlBase Model=OS-Atlas-Pro-7B, Learning Strategy=Supervised Fine-Tuning, Training Source=AndroidControl2026.01 | 74.68 | 40.8 | 24 | |
| Zero-ShotBase Model=OS-Atlas-Pro-7B, Learning Strategy=Zero-Shot2026.01 | 74.22 | 54.71 | 60 | |
| CL from AITZ and AndroidControlBase Model=OS-Atlas-Pro-7B, Learning Strategy=Continual Learning, Training Source=AITZ, AndroidControl2026.01 | 73.85 | 39.95 | 30 |