MathArena/arxivmath-1225
收藏资源简介:
--- dataset_info: features: - name: problem_idx dtype: int64 - name: answer dtype: string - name: problem_type list: string - name: source dtype: float64 - name: problem dtype: string splits: - name: train num_bytes: 11546 num_examples: 17 download_size: 12584 dataset_size: 11546 configs: - config_name: default data_files: - split: train path: data/train-* license: cc-by-sa-4.0 language: - en pretty_name: ArXivMath December 2025 size_categories: - n<1K --- ### Homepage and repository - **Homepage:** [https://matharena.ai/](https://matharena.ai/) - **Repository:** [https://github.com/eth-sri/matharena](https://github.com/eth-sri/matharena) ### Dataset Summary This dataset contains the questions from ArXivMath December 2025 used for the MathArena Leaderboard ### Data Fields Below one can find the description of each field in the dataset. - `problem_idx` (int): Index of the problem in the competition - `problem` (str): Full problem statement - `answer` (str): Ground-truth answer to the question - `problem_type` (sequence[string]): Type of the problem, either "Combinatorics", "Number Theory", "Algebra", "Geometry". One problem can have several types. ### Licensing Information This dataset is licensed under the Attribution-ShareAlike 4.0 International (CC BY-SA 4.0). Please abide by the license when using the provided data. ### Citation Information ``` @misc{balunovic_srimatharena_2025, title = {MathArena: Evaluating LLMs on Uncontaminated Math Competitions}, author = {Mislav Balunović and Jasper Dekoninck and Ivo Petrov and Nikola Jovanović and Martin Vechev}, copyright = {MIT}, url = {https://matharena.ai/}, publisher = {SRI Lab, ETH Zurich}, month = feb, year = {2025}, } ```
数据集信息: 特征: - 名称:problem_idx,数据类型:int64 - 名称:answer,数据类型:字符串 - 名称:problem_type,数据类型:字符串序列 - 名称:source,数据类型:float64 - 名称:problem,数据类型:字符串 拆分: - 名称:训练集(train),字节占用:11546,样本数量:17 下载大小:12584,数据集总大小:11546 配置项: - 配置名称:default(默认),数据文件: - 拆分:训练集,路径:data/train-* 许可证:CC BY-SA 4.0 语言:英语 展示名称:ArXivMath 2025年12月版 大小类别:样本数少于1000(n<1K) ### 主页与仓库 - **主页**:[https://matharena.ai/](https://matharena.ai/) - **仓库**:[https://github.com/eth-sri/matharena](https://github.com/eth-sri/matharena) ### 数据集概述 本数据集收录了用于MathArena排行榜的2025年12月版ArXivMath竞赛题目。 ### 数据字段 以下为数据集各字段的详细说明: - `problem_idx`(整数型):该问题在竞赛中的索引编号 - `problem`(字符串型):完整的题目陈述文本 - `answer`(字符串型):该问题的标准答案 - `problem_type`(字符串序列):问题所属类型,可选值为组合数学(Combinatorics)、数论(Number Theory)、代数(Algebra)、几何(Geometry),单个问题可对应多种类型。 ### 许可信息 本数据集采用知识共享署名-相同方式共享4.0国际许可协议(CC BY-SA 4.0)进行授权,使用本数据集时请严格遵守该许可协议的相关条款。 ### 引用信息 @misc{balunovic_srimatharena_2025, title = {MathArena: 面向无训练污染数学竞赛的大语言模型评测(原标题:MathArena: Evaluating LLMs on Uncontaminated Math Competitions)}, author = {Mislav Balunović、Jasper Dekoninck、Ivo Petrov、Nikola Jovanović、Martin Vechev}, copyright = {MIT}, url = {https://matharena.ai/}, publisher = {苏黎世联邦理工学院SRI实验室(SRI Lab, ETH Zurich)}, month = 2月, year = {2025}, }




