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

Agentic AI workflow benchmark

Benchmarks

Task NameDataset NameSOTA ResultTrend
Safety Risk Detectioninternal Agentic AI workflow benchmark
Precision100
29
Adversarial Attack DetectionAgentic AI workflow benchmark internal
Precision100
14
Showing 2 of 2 rows