Benchmark - 1

2026 (2)

March (2)

security: CTI-REALM: A new benchmark for end-to-end detection rule generation with AI agents

Microsoft Security Blog

2026-03-20

Microsoft introduced CTI-REALM, an open-source benchmark for evaluating AI agents on end-to-end detection engineering. It measures whether agents can turn cyber threat intelligence into validated detection rules.

security: From transparency to action: What the latest Microsoft email security benchmark reveals

Microsoft Security Blog

2026-03-12

Microsoft published a blog post about its latest email security benchmarking data, comparing Microsoft Defender’s mitigation of modern email threats against SEG and ICES vendors. The post says the benchmark is intended to move from transparency to action.