UGMathBench/ugmathbench

UGMathBench是一个评估大一大二学生数学推理能力的多样化动态基准数据集，包含16个科目和111个主题的5062个问题，每个问题有三个随机版本。这些科目包括抽象代数、算术、单变量微积分、复分析、金融数学、线性代数、概率、统计、代数、多变量微积分、组合数学、微分方程、几何、数论、集合论与逻辑以及三角学。UGMathBench is a diverse and dynamic benchmark for evaluating undergraduate-level mathematical reasoning, containing 5,062 problems across 16 subjects and 111 topics, with each problem having three randomized versions. These subjects include Abstract algebra, Arithmetic, Calculus_-_single_variable, Complex analysis, Financial mathematics, Linear algebra, Probability, Statistics, Algebra, Calculus_-_multivariable, Combinatorics, Differential equations, Geometry, Number theory, Set theory and logic, and Trigonometry.