# PentestBench | OpenHack > PentestBench v1 is a white-box pentesting benchmark maintained by OpenHack. It evaluates models and harnesses on 17 modern web applications with 761 planted vulnerabilities, including vulnerability-chain scenarios. Published NOV 16, 2026. Every evaluated tool receives the application source code; the reference vulnerability catalog stays sealed. Results describe each model and harness configuration working together. Recall, precision, and catalog F1 measure matches against the planted vulnerability catalog. The application corpus is planned for open-source release. Black-box pentesting benchmarks are coming soon. Cloud deployments, reachability evaluation, and false-positive identification are planned for future versions. ## Resources - [PentestBench](/): Benchmark overview and public results. - [Leaderboard](/#leaderboard): First full pass results, ranked by catalog F1. - [Application corpus](/#dataset): Applications and planted vulnerability counts. - [FAQ](/#faq): Purpose, evaluation scope, vulnerability chaining, and future plans. - [Full benchmark text](/llms-full.txt): Self-contained overview, results, dataset, and FAQ. - [Citation](/pentestbench-v1.bib): BibTeX citation for PentestBench v1. - [OpenHack](https://openhack.com): The always-on AI security engineer.