RealVuln: Benchmarking Rule-Based, General-Purpose LLM, and Security-Specialized Scanners on Real-World Code

Computer Science > Cryptography and Security [Submitted on 15 Apr 2026] RealVuln: Benchmarking Rule-Based, General-Purpose LLM, and Security-Specialized Scanners on Real-World Code John Pellew, Faizan Raza How do security scanners perform on real-world code? We present RealVuln, the first open-source benchmark comparing Rule-Based SAST, General-Purpose LLMs, and Security-Specialized scanners on 26 intentionally vulnerable Python repositories (educational and Capture-The-Flag applications) with 796 hand-labeled entries (676 vulnerabilities, 120 false-positive traps). We test 15 scanners (3 Rule-Based SAST, 10 General-Purpose LLM, 2 Security-Specialized) and rank them by F3 score (beta=3, weighting recall 9x over precision). A clear three-tier ranking emerges under all metrics. Under F3, the Security-Specialized scanner this http URL (73.0) leads, followed by the best General-Purpose LLM, Claude Sonnet 4.6 (51.7), which in turn scores nearly 3x higher than the best Rule-Based tool, Semgrep (17.7). Under F1, Sonnet 4.6 leads (60.9) with this http URL at 52.4. Rankings within tiers shift with beta, but the three-tier hierarchy holds across all weightings. All code, ground-truth data, scanner outputs, and scoring scripts are released under an open-source license. An interactive dashboard is at this https URL. RealVuln is a living benchmark: versioned, community-driven, with a roadmap toward multi-language coverage. Comments: 16 pages, 2 figures, 4 tables. Code and data: this https URL. Dashboard: this https URL Subjects: Cryptography and Security (cs.CR) ACM classes: K.6.5; D.2.5 Cite as: arXiv:2604.13764 [cs.CR]   (or arXiv:2604.13764v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.13764 Focus to learn more Submission history From: Faizan Raza [view email] [v1] Wed, 15 Apr 2026 11:49:29 UTC (50 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)