Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

CyberSecEval dataset and benchmarks · SOTA2 Research

Research Datasets

CyberSecEval

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Secure Code Generation

CyberSecEval SCG

79.06Safety

17

Insecure Coding Practice

CyberSecEval Instruction 1.0

72.1C Score

14

Insecure Coding Practice

CyberSecEval Autocomplete 1

85.9C

14

Secure Code Generation

CYBERSECEVAL

79.38Autocomplete

8

Cybersecurity Attack Success Rate

CyberSecEval

100CyberSecEval ASR

4

Content Safety Detection

CyberSecEval

92.2F1 Score

2

Malicious Cyberactivity

CyberSecEval MITRE

57.1Refusal Rate

2

Secure Code Generation

CyberSecEval Instruct

86.01Secure Code Generation (%)

2

Prompt Injection Robustness

CyberSecEval 2

91Robustness

2

Popular tasks

Secure Code Generation Insecure Coding Practice Prompt Injection Robustness Cybersecurity Attack Success Rate Malicious Cyberactivity

Follow for updates

Join SOTA2 Contact