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

Tutor Jailbreak

Benchmarks

Task NameDataset NameSOTA ResultTrend
Instruction Hierarchy RobustnessTutor Jailbreak user (dev)
Non-violation Rate99
2
Instruction Hierarchy RobustnessTutor Jailbreak sys-user
Non-violation Rate99
2
Showing 2 of 2 rows