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

Language

Benchmarks

Task NameDataset NameSOTA ResultTrend
Prompt Injection DetectionLanguage Direct Prompt Injection
FPR0
7
ClassificationLanguage (test)
Accuracy96.16
4
Language ModelingLanguage
Cross-Entropy Loss2.708
2
Showing 3 of 3 rows