TreeAILab/NumericBench
收藏官方服务：
资源简介：
NumericBench是一个评估大型语言模型数值推理能力的数据集，它包含多种类型的数据，如合成数字列表、现实世界的股票趋势和天气模式等。该数据集旨在全面测试LLM在结构化和噪声环境下的数值推理能力。
NumericBench is a dataset designed to evaluate the numerical reasoning capabilities of large language models, containing various types of data such as synthetic number lists, real-world stock trends, and weather patterns. It aims to comprehensively test the numerical reasoning ability of LLMs in both structured and noisy environments.
提供机构：
TreeAILab
