Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
GUI Navigation on Online-Mind2Web (Easy)
Loading...
78.31
Success Rate
Ovis2.5S-RF++
33.2052
44.9151
56.625
68.3349
Feb 14, 2026
Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
Ovis2.5S-RF++
Training Method=REINFO...
2026.02
78.31
Ovis2.5S-GRPO
Training Method=GRPO (...
2026.02
77.11
Ovis2.5S-RLOO
Training Method=RLOO (...
2026.02
75.9
Claude 3.7 Sonnet CU
Model Type=Proprietary
2026.02
72.84
Claude 4 Sonnet CU
Model Type=Proprietary
2026.02
71.6
Ovis2.5SFT
Training Method=SFT
2026.02
66.27
UI-TARS
Model Scale=7B, Versio...
2026.02
57.83
Qwen3-VL
Model Scale=32B
2026.02
38.55
Qwen3-VL
Model Scale=8B
2026.02
34.94
Feedback
Search any
task
Search any
task