Snyk VulnBench JavaScript 1.0: Can LLMs Find the Same Bugs Twice?

A new benchmark, Snyk VulnBench JavaScript 1.0, reveals that large language models (LLMs) produce inconsistent vulnerability findings across repeated scans of the same JavaScript code, with 80 of 161 unique unmatched findings appearing in only one of five identical runs. In contrast, reference-matched findings were stable, and Snyk Code's deterministic SAST tool outperformed LLMs in systematically enumerating data-flow sinks. The results suggest combining agentic LLM review with deterministic SAST rather than using either alone.

Computer Science Cryptography and Security Submitted on 14 Jun 2026 Title:Snyk VulnBench JS 1.0: Can LLMs Find the Same Bugs Twice? View PDF /pdf/2606.15762 HTML experimental https://arxiv.org/html/2606.15762v1 Abstract:We ran 300 repeated vulnerability-finding scans to measure how repeatable agentic large language model LLM security review is on the same JavaScript code, prompt, and benchmark harness. The headline result is that LLM security findings were unevenly repeatable: reference-matched findings were stable, but extra model reports varied heavily from run to run. Across 250 model runs, 80 of 161 unique unmatched findings appeared in only one of five identical repetitions, while only 22 appeared in all five. By contrast, when Claude matched a Snyk Code reference finding, the behavior was much more stable: 134 of 158 unique reference-matched findings appeared in all five repetitions. The benchmark also shows complementarity. Models consistently found familiar, high-signal exploit shapes, and in one case surfaced a likely Snyk Code product gap. Snyk Code static application security testing SAST was deterministic and better at systematically enumerating repeated data-flow sinks. The results support combining agentic LLM review with deterministic SAST rather than treating either technique as a replacement for the other. Current browse context: cs.CR References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .