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

Agent Safety Judgment on ROME SDM unsafe

100F1 Score

Claude Sonnet 4.6

92.77294.648596.52598.4015May 5, 2026
Updated 28d ago

Evaluation Results

MethodLinks
2026.05
10010097
2026.05
98.4897100
2026.05
98.4396.9197
2026.05
93.0587100