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

Malicious Code Generation

Benchmarks

Task NameDataset NameSOTA ResultTrend
Malicious Code GenerationMalicious Code Generation
Refusal Rate (Overall)97
15
Malicious Code Generation DetectionMalicious Code Generation Super Suffix
Benign Probability Score0.96
10
Malicious Code Generation DetectionMalicious Code Generation Primary Suffix
Benign Probability52
10
Malicious Code Generation DetectionMalicious Code Generation No Suffix
Benign Probability Score0.76
10
Showing 4 of 4 rows