Published on February 9, 2026, VulnLLM-R-7B is presented as a reasoning model that searches code for vulnerabilities by examining data and control flows.
On February 9, 2026, VulnLLM-R-7B was presented as a reasoning model designed to search code for vulnerabilities. Its description says it analyzes data and control flows; engineers can evaluate the model and its suitability for vulnerability-analysis workflows.
The project page provides access to the model. To check the announcement and its details, consult the original publication and verify its technical description and access conditions there; the supplied material reports no evaluation results or detection rates.