Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Do-Not-Answer

Benchmarks

Task NameDataset NameSOTA ResultTrend
Safety AlignmentDo-Not-Answer
MD0
36
Safety EvaluationDo-Not-Answer (test)
ASR3.195
9
Jailbreak Attack EvaluationDo-Not-Answer
ASR2.5
6
Language ModelingDo-Not-Answer
PPL154.81
1
Showing 4 of 4 rows