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

Safety Classification on BeaverTails (test)

94AUC

Separate Guardrail 7B

55.5265.5175.585.49May 30, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
94
2025.05
94
2025.05
93
2025.05
93
2025.05
93
2025.05
92
2025.05
91
2025.05
91
2025.05
91
2025.05
91
2025.05
91
2025.05
91
2025.05
90
2025.05
90
2025.05
90
2025.05
90
2025.05
89
2025.05
89
2025.05
89
2025.05
86
2025.05
85
2025.05
79
2025.05
73
2025.05
57