---
title: "Microsoft’s multi-agent AI system tops Anthropic’s Mythos on cybersecurity benchmark"
date: 2026-05-13
source: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a0516f4e48c4c1da53cbb0d80d29eb0&url=https%3a%2f%2fwww.msn.com%2fen-us%2fnews%2ftechnology%2fmicrosoft-s-multi-agent-ai-system-tops-anthropic-s-mythos-on-cybersecurity-benchmark%2far-AA238473&c=4670687872792239632&mkt=en-us
description: "Microsoft's new vulnerability-scanning system, codenamed MDASH, scored 88.45% on the CyberGym benchmark, surpassing single-model systems from Anthropic and OpenAI by using more than 100 specialized AI ..."
---

# Microsoft’s multi-agent AI system tops Anthropic’s Mythos on cybersecurity benchmark

Microsoft's new vulnerability-scanning system, codenamed MDASH, scored 88.45% on the CyberGym benchmark, surpassing single-model systems from Anthropic and OpenAI by using more than 100 specialized AI ...

*Published: 2026-05-13*