List your company

GUI Agent Navigation on GUI-Odyssey (test)

66Type AccuracyWebFactory-3B
36.3644.05551.7559.445Mar 5, 2026

Evaluation results

MethodLinks
WebFactory-3BSetting=RL Fine-Tuning2026.036648.140.9
GUI-R1-3BSetting=RL Fine-Tuning2026.0354.841.541.3
QwenVL2.5-3BSetting=Zero-Shot2026.0338.427.227.2
GPT-4oSetting=Zero-Shot2026.0337.514.25.4