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

CyberSecEval

Benchmarks

Task NameDataset NameSOTA ResultTrend
Secure Code GenerationCyberSecEval SCG
Safety79.06
17
Insecure Coding PracticeCyberSecEval Instruction 1.0
C Score72.1
14
Insecure Coding PracticeCyberSecEval Autocomplete 1
C85.9
14
Cybersecurity Attack Success RateCyberSecEval
CyberSecEval ASR100
4
Prompt Injection RobustnessCyberSecEval 2
Robustness91
2
Showing 5 of 5 rows