ncbi/MedCalc-Bench-v1.2

MedCalc-Bench是首个用于评估大型语言模型（LLMs）作为临床计算器能力的医学计算数据集。每个实例包含患者笔记、要求计算特定临床值的问题、最终答案值以及解释如何获得最终答案的逐步解决方案。数据集覆盖55种不同的计算任务，分为基于规则的计算和基于方程的计算。训练集包含10,543个实例，测试集包含1,100个实例。数据集旨在提高LLMs在医学环境中的计算推理能力。

MedCalc-Bench is the first medical calculation dataset used to benchmark LLMs ability to serve as clinical calculators. Each instance in the dataset consists of a patient note, a question asking to compute a specific clinical value, a final answer value, and a step-by-step solution explaining how the final answer was obtained. The dataset covers 55 different calculation tasks which are either rule-based calculations or are equation-based calculations. It contains a training dataset of 10,543 instances and a testing dataset of 1,100 instances. The dataset aims to improve the computational reasoning skills of LLMs in medical settings.