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

Safety Classification on OS Bench

0.936Recall

CLUE

0.215280.402390.58950.77661Dec 31, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.12
0.9360.8620.871
2024.12
0.4160.6090.515
2024.12
0.3990.6090.505
2024.12
0.320.6080.449
2024.12
0.2970.6250.441
2024.12
0.2640.6220.41
2024.12
0.2610.6120.401
2024.12
0.2430.5990.377