HMMT25

### 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 HMMT February 2025 used for the MathArena Leaderboard

### Data Splits & Files

- **test split**: `data/test/test.jsonl` (30 samples)

### Fields
- `problem_idx` (int): Index of the problem
- `problem` (str): Full problem statement
- `answer` (str): Ground-truth answer
- `problem_type` (sequence[string]): e.g. "Combinatorics", "Number Theory", "Algebra", "Geometry"

### Licensing Information

This dataset is licensed under the Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-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},
}
```

### 主页与代码仓库
- **主页**：[https://matharena.ai/](https://matharena.ai/)
- **代码仓库**：[https://github.com/eth-sri/matharena](https://github.com/eth-sri/matharena)

### 数据集概览
本数据集收录了用于MathArena排行榜评测的2025年哈佛大学-麻省理工学院数学锦标赛（Harvard-MIT Math Tournament，简称HMMT）二月赛试题。

### 数据划分与文件
- **测试集划分**：`data/test/test.jsonl`（共30个样本）

### 数据字段
- `problem_idx`（整数类型）：试题索引
- `problem`（字符串类型）：完整试题题干
- `answer`（字符串类型）：标准答案
- `problem_type`（字符串序列类型）：试题所属类别，例如“组合数学”、“数论”、“代数”、“几何”

### 授权信息
本数据集采用知识共享署名-非商业性使用-相同方式共享4.0国际许可协议（Attribution-NonCommercial-ShareAlike 4.0 International，CC BY-NC-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：在无训练污染的数学竞赛中评测大语言模型（Large Language Model，LLM)},
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},
}