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

Safety Classification on BeaverTails 3k (test)

94.7Animal Safety Classification Accuracy

AR Relation

63.08471.29279.587.708Oct 21, 2025
Updated 22d ago

Evaluation Results

MethodLinks
2025.10
94.794.481.284.991.885.670.76264.886.889.592867883
2025.10
92.795.376.579.881.781.779.751.166.389.378.990.872.472.579.2
2025.10
85.891.366.176.278.980.674.851.259.385.179.591.152.255.673.4
2025.10
64.357.453.652.261.16352.950.751.258.573.668.252.251.557.9