AIME 2025 Dataset

  Dataset Description

This dataset contains problems from the American Invitational Mathematics Examination (AIME) 2025-I & II.

Homepage and repository

Homepage: https://matharena.ai/ Repository: https://github.com/eth-sri/matharena

  Dataset Summary

This dataset contains the questions from AIME 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… See the full description on the dataset page: https://huggingface.co/datasets/MathArena/aime_2025.

letta-ai/stateful-aime-2025 dataset hosted on Hugging Face and contributed by the HF Datasets community

Combined AIME 2021-2025 dataset

This dataset is a combination of:

AI-MO/aimo-validation-aime Sunny8781/AIME2025_w_solution

with the latter being slightly changed to follow AI-MO's format, namely

changing id from str to int and updating ids to follow previous ones changing answer from int to str and adding starting "0" to 2 digit answers add urls

note that the AIME 2025 answers contain only a single answer (the first one) whereas the AIME 2021-2024 answers contain all of them… See the full description on the dataset page: https://huggingface.co/datasets/allenai/aime-2021-2025.

CMU-AIRe/hmmt-aime-2025 dataset hosted on Hugging Face and contributed by the HF Datasets community

sea-snell/aime-2025 dataset hosted on Hugging Face and contributed by the HF Datasets community

pe-nlp/DAPO-AIME-2025 dataset hosted on Hugging Face and contributed by the HF Datasets community

实时更新的大模型数学能力评测排行榜 - GSM8K/MATH/AIME 2024/AIME 2025权威基准对比排名，包括 AIME2025, AIME 2024, MATH-500, GSM8K 等。提供详细对比，帮助开发者评估模型。

sea-snell/aime-2025-split-into-parts dataset hosted on Hugging Face and contributed by the HF Datasets community

TianHongZXY/aime-1983-2025 dataset hosted on Hugging Face and contributed by the HF Datasets community

Comparison of Represents the average of math benchmarks in the Artificial Analysis Intelligence Index (AIME 2024 & Math-500) by Model

Prévision météorologique de la ville de Aime par Météo Villes

Homepage and repository

Homepage: https://matharena.ai/ Repository: https://github.com/eth-sri/matharena

  Dataset Summary

This dataset contains model answers to the questions from AIME 2025 generated using the MathArena GitHub repository.

  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 gold_answer (str): Ground-truth answer to the… See the full description on the dataset page: https://huggingface.co/datasets/MathArena/aime_2025_outputs.

Prévision météorologique de la ville de La Côte-d'Aime par Météo Villes

PATROCINADO | Protección construye caminos hacia pensiones tranquilas y dignas por medio de la libertad económica y diversas alternativas.

AIME2025-ko: Korean Translation of the AIME Mathematics Benchmark

Korean Version README

AIME2025-ko is a Korean adaptation of the AIME-2025 (American Invitational Mathematics Examination) benchmark, originally used with the lighteval framework. This version is designed for evaluating the mathematical reasoning capabilities of large language models (LLMs) in the Korean language using the lighteval framework.

  Dataset Details

Original Source: AIME2025 benchmark from… See the full description on the dataset page: https://huggingface.co/datasets/allganize/AIME2025-ko.

GY2233/AIME-2024-2025 dataset hosted on Hugging Face and contributed by the HF Datasets community

Homepage and repository

Homepage: https://matharena.ai/ Repository: https://github.com/eth-sri/matharena

  Dataset Summary

This dataset contains model answers to the questions from BRUMO 2025 generated using the MathArena GitHub repository.

  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 gold_answer (str): Ground-truth answer to the… See the full description on the dataset page: https://huggingface.co/datasets/MathArena/brumo_2025_outputs.

jdchang/distill-r1-qwen-1.5b-aime-2025 dataset hosted on Hugging Face and contributed by the HF Datasets community

Disclaimer: This is a Benchmark dataset! Do not using in training! This is the Benchmark of AIME from year 1983~2023, and 2024(part 2). Original: https://artofproblemsolving.com/wiki/index.php/AIME_Problems_and_Solutions 2024(part 1) can be find at https://huggingface.co/datasets/AI-MO/aimo-validation-aime.

  Citation

@misc {di_zhang_2025, author = { {Di Zhang} }, title = { AIME_1983_2024 (Revision 6283828) }, year = 2025, url = {… See the full description on the dataset page: https://huggingface.co/datasets/di-zhang-fdu/AIME_1983_2024.