CrowdStrike, in partnership with Meta, today announced CyberSOCEval, a new suite of open-source benchmarks at Fal.Con 2025 to evaluate AI systems in real-world security operations. Built on Meta’s CyberSecEval framework and CrowdStrike’s leading threat intelligence, CyberSOCEval tests large language models (LLMs) across critical SOC workflows, such as incident response, malware analysis, and threat analysis comprehension, enabling organizations to adopt AI with confidence.
Cyber defenders face overwhelming alert volumes and evolving threats, necessitating advanced AI to stay ahead. Many SOCs are early in their AI adoption, struggling to identify effective LLMs for automation and efficiency. CyberSOCEval addresses this by providing a standardized framework to test LLMs against real-world adversary tradecraft and expert-designed scenarios, ensuring operational readiness under pressure.
The suite leverages Meta’s open-source CyberSecEval framework and CrowdStrike’s frontline threat intelligence, evaluating LLMs across key workflows:
This enables security teams to pinpoint high-value AI use cases and developers to refine models for better SOC outcomes. “At Meta, we’re committed to advancing and maximizing the benefits of open source AI,” said Vincent Gonguet, Director of Product, GenAI at Superintelligence Labs at Meta. “With these benchmarks in place, and open for the security and AI community to further improve, we can more quickly work as an industry to unlock the potential of AI in protecting against advanced attacks, including AI-based threats.”
“When two leaders like CrowdStrike and Meta come together, it’s about setting the direction of cybersecurity for the AI era,” said Daniel Bernard, Chief Business Officer at CrowdStrike. “This partnership sets a new bar for how AI in the SOC should be built and deployed, empowering defenders to stay ahead of the adversary.”
CyberSOCEval is now available via Meta’s CyberSecEval framework, encouraging community contributions to enhance AI capabilities in cybersecurity. For more details, visit Meta’s CyberSecEval framework or CrowdStrike’s partner page. The open-source nature fosters collaboration, enabling developers and security teams to refine AI models for real-world threats.
As of September 15, 2025, CrowdStrike’s stock (NASDAQ: CRWD) is priced at $444.455, up from $436.1, with a market cap of $109.44 billion. The stock has risen 58.4% year-over-year from $280.47 in September 2024, reflecting strong market confidence in its AI-native cybersecurity leadership (see finance card above). This partnership with Meta further solidifies CrowdStrike’s position in advancing AI-driven SOC solutions.
CrowdStrike (NASDAQ: CRWD), a global cybersecurity leader, has redefined modern security with the world’s most advanced cloud-native platform for protecting critical areas of enterprise risk – endpoints and cloud workloads, identity, and data. Powered by the CrowdStrike Security Cloud and world-class AI, the Falcon® platform delivers hyper-accurate detections, automated protection, elite threat hunting, and prioritized vulnerability observability.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.