SecLLMHolmes

Evals

Benchmark / dataset

Tests LLMs' ability to identify and reason about vulns.

Category
Secure code & vuln detection
Insurance exposure
Breach/cyber
Publisher
Boston University
Publisher type
Academic
License
GPL-3.0
Status
Stale (>12mo)
Last commit
2025-05-04
Stars
68

View source on GitHub →

Wanich Risk Lab, 2026.