Benchmark Radar™
Star —

SEC-bench

Explore score history ↗

SEC-bench Pro measures long-horizon vulnerability discovery in software security. It includes 344 verified vulnerabilities across V8, SpiderMonkey, and Linux kernel, each paired with instructions for reproducing a working proof-of-concept. Grading uses an LLM-based judge to classify generated PoCs against vulnerable, fixed, and latest images.

Released
2026-05-26
Institutions
University of Illinois Urbana-Champaign
Evaluates
Cybersecurity, Language & Knowledge, cs.CR
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

SEC-bench paper and code

No reported scores are on record for this benchmark yet.

Which sources cite SEC-bench?

Related Cybersecurity, Language & Knowledge, cs.CR benchmarks