Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Agent Safety Judgment on ROME Shortcut Decision-Making 1.0

94.53F1-Score

ARISE (Std)

38.640453.150267.6682.1698May 5, 2026
Updated 28d ago

Evaluation Results

MethodLinks
2026.05
94.53
2026.05
88.67
2026.05
88.21
2026.05
87.56
2026.05
86.36
2026.05
86.36
2026.05
85.97
2026.05
84.55
2026.05
81.18
2026.05
77.87
2026.05
77.6
2026.05
74.9
2026.05
71.24
2026.05
70.65
2026.05
63.83
2026.05
62.75
2026.05
61.73
2026.05
61.22
2026.05
54.65
2026.05
51.37
2026.05
47.96
2026.05
46.84
2026.05
43.43
2026.05
40.79