SecCodeBench is a benchmark suite focusing on evaluating the security of code generated by large language models (LLMs).
Like alibaba/sec-code-bench, 0 likes 0 Bookmark alibaba/sec-code-bench, 0 bookmarks 0 [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents
Like AI-secure/RedCode, 0 likes 0 Bookmark AI-secure/RedCode, 0 bookmarks 0 [ICML 2026] Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks
Like LeiLiLab/susvibes, 0 likes 0 Bookmark LeiLiLab/susvibes, 0 bookmarks 0 Benchmarking repository-borne prompt injection attacks and lightweight defenses for local coding agents. DL4C @ ICML 2026.
Like DaoyuanLi2816/RepoGuardBench, 0 likes 0 Bookmark DaoyuanLi2816/RepoGuardBench, 0 bookmarks 0 BoundaryBench: benchmark coding-agent harnesses (Claude Code, Codex, Terminus 2, Grok) on Terminal-Bench tasks under hardened NIST-derived sandbox policies. Inspect AI + Harbor compatible.
Like boundary-bench/boundary-bench, 0 likes 0 Bookmark boundary-bench/boundary-bench, 0 bookmarks 0 PatchEval: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities
Like bytedance/PatchEval, 0 likes 0 Bookmark bytedance/PatchEval, 0 bookmarks 0 CVE-bench — conformant reproduce-and-fix security benchmark from public CVEs + OSS fix-PRs/tests. Apply-patch -> run the security test (FAIL->PASS). Cost-Pareto leaderboard, PR-based submissions, nightly CI.
Like ruvnet/CVE-bench, 0 likes 0 Bookmark ruvnet/CVE-bench, 0 bookmarks 0 
