List your company

GUI Navigation on Online-Mind2Web (Medium)

66.91Success RateClaude 3.7 Sonnet CU
24.228435.309246.3957.4708Feb 14, 2026

Evaluation results

MethodLinks
Claude 3.7 Sonnet CUModel Type=Proprietary2026.0266.91
Ovis2.5S-RF++Training Method=REINFORCE++ (Step-wise)2026.0265.73
Claude 4 Sonnet CUModel Type=Proprietary2026.0265.47
Ovis2.5S-GRPOTraining Method=GRPO (Step-wise)2026.0262.94
Ovis2.5S-RLOOTraining Method=RLOO (Step-wise)2026.0260.84
Ovis2.5SFTTraining Method=SFT2026.0251.75
Qwen3-VLModel Scale=32B2026.0227.97
UI-TARSModel Scale=7B, Version=1.52026.0227.27
Qwen3-VLModel Scale=8B2026.0225.87