MathArena/aime_2025_outputs

该数据集包含了MathArena GitHub仓库生成的AIME 2025竞赛问题的模型答案。数据集字段包括问题索引、完整问题陈述、真实答案、模型名称、模型配置路径、答案尝试索引、用户消息、模型答案、解析后的答案、答案是否正确、输入和输出令牌数、总成本、每百万输入和输出令牌的成本。数据集分为训练集，大小约为4560个示例，总数据大小为102467193字节。数据集遵循知识共享署名-非商业性使用-相同方式共享4.0国际许可证。

This dataset contains model answers to the questions from AIME 2025 generated using the MathArena GitHub repository. The dataset fields include problem index, full problem statement, ground-truth answer, model name, model config path, answer attempt index, user message, model answer, parsed answer, correctness of the answer, number of input and output tokens, total cost, and cost per million input and output tokens. The dataset is split into a training set with approximately 4560 examples, totaling 102467193 bytes in size. The dataset is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.