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

LLM Safety Evaluation on BeaverTails

9.88Ssafe Score

LANCE

4.35765.79137.2258.6587May 8, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.05
9.888.038.25
2026.05
9.868.038.02
2026.05
9.7987.98
2026.05
9.748.018.03
2026.05
9.737.988.02
2026.05
9.597.587.9
2026.05
9.553.416.71
2026.05
9.347.798.61
2026.05
9.276.567.67
2026.05
9.237.898.69
2026.05
9.217.567.84
2026.05
9.184.177
2026.05
9.036.657.86
2026.05
8.47.217.74
2026.05
7.667.027.63
2026.05
5.916.457.45
2026.05
5.886.217.28
2026.05
4.575.597.04