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

OOD Safety Suite

Benchmarks

Task NameDataset NameSOTA ResultTrend
Safety Alignment EvaluationOOD Safety Suite Average of SorryBench, AdvBench, and HEx-PHI
Average Absolute Improvement0.5
12
Showing 1 of 1 rows