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

RealGuardrails

Benchmarks

Task NameDataset NameSOTA ResultTrend
Instruction Hierarchy RobustnessRealGuardrails Handwritten
Score89
2
Instruction Hierarchy RobustnessRealGuardrails Distractors
Score0.95
2
Showing 2 of 2 rows