https://github.com/alibaba/sec-code-bench

SecCodeBench is a benchmark suite focusing on evaluating the security of code generated by large language models (LLMs).
https://github.com/alibaba/sec-code-bench

benchmark datasets llm security

Last synced: 8 months ago
JSON representation

SecCodeBench is a benchmark suite focusing on evaluating the security of code generated by large language models (LLMs).

• Host: GitHub
• URL: https://github.com/alibaba/sec-code-bench
• Owner: alibaba
• License: apache-2.0
• Created: 2025-07-07T09:35:05.000Z (12 months ago)
• Default Branch: main
• Last Pushed: 2025-08-11T09:42:40.000Z (11 months ago)
• Last Synced: 2025-08-11T11:35:40.859Z (11 months ago)
• Topics: benchmark, datasets, llm, security
• Language: Java
• Homepage:
• Size: 4.15 MB
• Stars: 54
• Watchers: 0
• Forks: 7
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-AI-Security - SecCodeBench - code-bench?logo=github&label=&style=social)](https://github.com/alibaba/sec-code-bench) - 37 test cases / 16 CWEs; functionality-first pipeline; dynamic PoC exploits + static checks; includes LLM-as-a-Judge; Gen & Fix modes. ([↑](#table-of-contents)Benchmarks <a name="benchmarking"></a> / **Code Security**)