ioi-test-cases

# IOI

The International Olympiad in Informatics (IOI) is one of five international science olympiads (if you are familiar with AIME, IOI is the programming equivalent of IMO, for which the very best students who take part in AIME are invited) and tests a very select group of high school students (4 per country) in complex algorithmic problems.

The problems are extremely challenging, and the full test sets are available and released under a permissive (CC-BY) license. This means that IOI is the perfect dataset to test a model's code reasoning capabilities.

See [Problem statements dataset](https://huggingface.co/datasets/open-r1/ioi) for more info.

## Loading tests
To load and parse tests for a given year (e.g., 2021):
```python
from datasets import load_dataset
from collections import defaultdict

tests_dataset = load_dataset("open-r1/ioi-test-cases", name="2021", split="train")

test_cases = defaultdict(dict)
for test_case in tests_dataset:
test_cases[test_case['problem_id']][test_case['test_name']] = test_case['test_input'], test_case['test_output']

```

You can then index test cases by their `test_name` value from `open-r1/ioi`

## Dataset links
- [Problem statements dataset](https://huggingface.co/datasets/open-r1/ioi) (IOI’2020 - IOI’2024): `open-r1/ioi`
- [Test cases](https://huggingface.co/datasets/open-r1/ioi-test-cases): `open-r1/ioi-test-cases` (you are here!)
- [Official (ground truth) solutions](https://huggingface.co/datasets/open-r1/ioi-sample-solutions): `open-r1/ioi-sample-solutions`
- [Evaluation data for 40+ leading models on IOI’2024](https://huggingface.co/datasets/open-r1/ioi-2024-model-solutions): `open-r1/ioi-2024-model-solutions`

## Generating solutions
To have models generate solutions to IOI problems, follow the instructions [here](https://github.com/huggingface/ioi/tree/main/generate).

## Running tests
To run tests on generated solutions, follow the instructions [here](https://github.com/huggingface/ioi/tree/main/run_tests).

## Original data
All data was extracted, parsed, and adapted from the official IOI Tasks, which are released under CC-BY:
- https://www.ioi2024.eg/competition-tasks
- https://ioi2023.hu/tasks/index.html
- https://ioi2022.id/tasks/
- https://ioi2021.sg/ioi-2021-tasks/
- https://ioi2020.sg/ioi-2020-tasks/

## License
Similarly to the original problem data, this and accompanying datasets are released under CC-BY.

# IOI
国际信息学奥林匹克竞赛（International Olympiad in Informatics，IOI）是全球五大国际学科奥林匹克赛事之一。若您熟悉美国数学邀请赛（American Invitational Mathematics Examination，AIME），IOI则相当于编程领域的国际数学奥林匹克（International Mathematical Olympiad，IMO）——受邀参赛者均为AIME中的顶尖选手。该赛事面向经严格选拔的高中生群体（每国选派4名选手），考核其解决复杂算法问题的能力。

赛事题目极具挑战性，完整赛题集以宽松的知识共享署名（CC-BY）许可协议发布。正因如此，IOI数据集是测试模型代码推理能力的绝佳素材。

如需了解更多信息，请参阅[赛题数据集](https://huggingface.co/datasets/open-r1/ioi)。

## 加载测试用例
如需加载并解析指定年份（如2021年）的测试用例，请执行以下代码：
python
from datasets import load_dataset
from collections import defaultdict

tests_dataset = load_dataset("open-r1/ioi-test-cases", name="2021", split="train")

test_cases = defaultdict(dict)
for test_case in tests_dataset:
test_cases[test_case['problem_id']][test_case['test_name']] = test_case['test_input'], test_case['test_output']

随后你可通过`open-r1/ioi`数据集中的`test_name`字段索引对应测试用例。

## 数据集链接
- [赛题数据集](https://huggingface.co/datasets/open-r1/ioi)（覆盖IOI’2020至IOI’2024赛事）：`open-r1/ioi`
- [测试用例集](https://huggingface.co/datasets/open-r1/ioi-test-cases)：`open-r1/ioi-test-cases`（即当前数据集）
- [官方（标准答案）题解](https://huggingface.co/datasets/open-r1/ioi-sample-solutions)：`open-r1/ioi-sample-solutions`
- [IOI’2024赛事40余款主流模型评测数据](https://huggingface.co/datasets/open-r1/ioi-2024-model-solutions)：`open-r1/ioi-2024-model-solutions`

## 生成题解
如需让模型生成IOI赛题的题解，请遵循[此处](https://github.com/huggingface/ioi/tree/main/generate)的操作指引。

## 运行测试
如需对生成的题解执行测试，请遵循[此处](https://github.com/huggingface/ioi/tree/main/run_tests)的操作指引。

## 原始数据
所有数据均从官方IOI赛题中提取、解析并整理而来，原始赛题以CC-BY许可协议发布：
- https://www.ioi2024.eg/competition-tasks
- https://ioi2023.hu/tasks/index.html
- https://ioi2022.id/tasks/
- https://ioi2021.sg/ioi-2021-tasks/
- https://ioi2020.sg/ioi-2020-tasks/

## 许可协议
与原始赛题数据一致，本数据集及配套数据集均以CC-BY许可协议发布。

搜集汇总

背景与挑战

背景概述

该数据集包含国际信息学奥林匹克竞赛（IOI）的测试用例，用于测试模型的代码推理能力，覆盖2020年至2024年的竞赛数据，遵循CC-BY许可。