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

Safety Evaluation on BeaverTails

99.4Safety Score

TELLME NT-Xent

66.22474.83783.4592.063Feb 7, 2025Apr 15, 2025Jun 21, 2025Aug 27, 2025Nov 2, 2025Jan 8, 2026Mar 17, 2026
Updated 6d ago

Evaluation Results

MethodLinks
2025.02
99.4
2025.02
99.1
2025.02
98
2025.02
97.6
2026.03
76.7
2026.03
70.5
2026.03
68
2026.03
67.5