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

Safety Alignment on Safety BeaverTails, HEx-PHI (test)

95.67BeaverTails Score

DASE

82.555685.960389.36592.7697Jan 29, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
95.6710097.84
2026.01
94.7910097.4
2026.01
94.3310097.16
2026.01
94.1695.294.68
2026.01
93.9498.3396.13
93.839996.41
2026.01
91.6299.6795.64
2026.01
89.9887.888.89
2026.01
88.9998.3393.66
2026.01
83.0685.6784.36