realvuln v3.1
Dashboard Leaderboard Methodology Dataset Findings Roadmap Journal Paper GitHub ↗
Living benchmark · v3.1 · Apache 2.0 · arXiv:2604.13764 · September 2026

RealVuln

An open benchmark measuring how Rule-Based SAST, General-Purpose LLM, and Security-Specialized scanners perform on real-world vulnerable code.

4,138
Vulnerabilities
280
False-positive traps
140
Repositories
741,034
Lines of code
33
Scanners tested

Leaderboard

Open full dashboard →

33 scanners on identical pinned commits across 140 repositories. Headline metric is F3 (strict): recall weighted nine times over precision, with unfinished repositories counted as misses. Switch between F2 and F3 to re-rank. Metric definitions →

Security-Specialized General-Purpose LLM Rule-Based SAST
F3 weights recall over precision · strict scoring counts unfinished repos as misses
# Scanner F3 Python F3 TS/JS F3 Missed Vulns Cost /100k LoC Cost/100 Vulns

Amber repo counts mark runs that did not complete all repositories of the selected corpus; under strict scoring their unscored repos count as misses. The Overall tab ranks only scanners that covered every language in the corpus; a run that covered one language appears on that language's tab instead, so every ranking is like-for-like. Cost is the total USD spend for the scored run; rule-based tools are free or variably priced (—).

Precision vs. recall, selected leaderboard. Security-Specialized systems (violet) reach the high-recall right; General-Purpose LLMs cluster center with strong precision; Rule-Based tools occupy the low-recall left.

Security-Specialized6 systems 86.4best F3 recall to 0.89
breadth-driven
General-Purpose LLM24 models 80.0best F3 range 23.3–80.0
high variance
Rule-Based SAST3 tools 23.1best F3 recall ≤ 0.19
syntactic only

Tier figures follow the selected leaderboard. On the Python leaderboard (66 repositories, where the most scanners have full coverage) a three-tier ordering — Security-Specialized > General-Purpose LLM > Rule-Based SAST — holds under both F2 and F3, though within-tier rankings shift with the metric and strict/standard mode. Read the analysis →