CyberSecEval

CyberSecEval is a suite of open source benchmarks designed to evaluate Large Language Models (LLMs) in the tasks of Malware Analysis and Threat Intelligence Reasoning, addressing critical gaps in current evaluations relevant to real-world cybersecurity scenarios.

Papers using CyberSecEval (1)

CyberSOCEval: Benchmarking LLMs Capabilities for Malware Analysis and Threat Intelligence Reasoning2025