Microsoft has released its first dedicated cybersecurity model, MAI-Cyber-1-Flash, and integrated it into MDASH, a vulnerability-hunting system that scored 95.95% on the CyberGym benchmark, according to the company. CyberGym asks AI agents to reproduce 1,507 known vulnerabilities across 188 open-source projects. MDASH’s score topped GPT-5.5 Cyber at 85.6%, Mythos 5 at 83.8%, GPT-5.6 Sol at 83.6%, and Gemini 3.5 Flash Cyber at 83.2%. Microsoft says MAI-Cyber-1-Flash handles up to 90% of the workload, while MDASH routes the hardest 10% to GPT-5.4. The combined setup costs 50% less than Microsoft’s current best MDASH configuration, according to the company. MDASH uses more than 100 specialized agents to audit code, debate findings, and build proof-of-concept demonstrations. The scanner is in private preview through Microsoft Defender, where teams can review findings and generate proposed fixes. Microsoft CEO Satya Nadella wrote that MAI-Cyber-1-Flash “delivers world-class performance at 50 percent of the cost of leading models.” The result is self-reported by Microsoft and had not appeared on CyberGym’s public leaderboard at publication time.