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

Agent Safety Judgment on ROME CA unsafe subset

97.35F1 Score

Claude Sonnet 4.6

89.591691.605893.6295.6342May 5, 2026
Updated 28d ago

Evaluation Results

MethodLinks
2026.05
97.3594.8597
2026.05
94.0588.7898
2026.05
91.8985100
2026.05
89.8981.6398