SECBENCH

该数据集名为SecBench，是一个多维度的基准测试数据集，旨在评估大型语言模型（LLM）在网络安全领域的表现。它包含了44,823个多选题（MCQs）和3,087个简答题（SAQs），这些问题以不同的语言和格式呈现。该数据集覆盖了不同能力级别的问题，支持多种语言，并涵盖了网络安全领域的多个子领域，使其成为评估网络安全领域LLM的最大和最全面的数据集之一。其规模达到了44,823个多选题和3,087个简答题，任务专注于评估网络安全领域的大型语言模型。

This dataset, named SecBench, is a multi-dimensional benchmark dataset designed to evaluate the performance of Large Language Models (LLMs) in the field of cybersecurity. It contains 44,823 Multiple-Choice Questions (MCQs) and 3,087 Short Answer Questions (SAQs), presented in a variety of languages and formats. Covering questions of varying difficulty levels, supporting multiple languages, and spanning multiple subfields within cybersecurity, it ranks among the largest and most comprehensive datasets for evaluating LLMs in the cybersecurity domain. With a total scale of 44,823 MCQs and 3,087 SAQs, its tasks focus on evaluating Large Language Models in the cybersecurity field.