Wloner0809/AIME25 dataset hosted on Hugging Face and contributed by the HF Datasets community

drproduck/aime25 dataset hosted on Hugging Face and contributed by the HF Datasets community

Source: math-ai/aime25 Modification:

Remove redundent columns

Keys:

problem answer

Size

test: 30

guanning/aime25 dataset hosted on Hugging Face and contributed by the HF Datasets community

Dataset card for aime25

This dataset was made with Curator.

  Dataset details

A sample from the dataset: { "question": "Find the sum of all integer bases $b>9$ for which $17_{b}$ is a divisor of $97_{b}$.", "reasoning": "Okay, let's see. The problem is to find the sum of all integer bases b > 9 where 17_b divides 97_b. Hmm.

First, I need to understand what 17_b and 97_b represent in base 10. In base b, the number 17_b would be 1*b + 7, right? Similarly, 97_b… See the full description on the dataset page: https://huggingface.co/datasets/JingzeShi/aime25.

flatlander1024/aime25-o3mini dataset hosted on Hugging Face and contributed by the HF Datasets community

AIME 2025 Dataset

  Dataset Description

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

HennersBro98/reasoning-aime25-nous dataset hosted on Hugging Face and contributed by the HF Datasets community

PrimeIntellect/AIME-25 dataset hosted on Hugging Face and contributed by the HF Datasets community

Dataset Card for Dataset Name

Generate 32 solutions for aime25 using deepseek-ai/DeepSeek-R1-Distill-Qwen-7B This dataset card aims to be a base template for new datasets. It has been generated using this raw template.

  Dataset Details





  Dataset Description

Columns:

problem: str original problem statement answer: str ground truth answer completion: List[str] generations by the model prediction: List[str] prediction extracted from generation score: List[float] is… See the full description on the dataset page: https://huggingface.co/datasets/drproduck/r1-qwen7b-aime25-n32.

HennersBro98/reasoning-aime25-deepscaler dataset hosted on Hugging Face and contributed by the HF Datasets community

HennersBro98/reasoning-aime25-evaluation-system1 dataset hosted on Hugging Face and contributed by the HF Datasets community

drproduck/r1-qwen7b-awq-aime25-n32 dataset hosted on Hugging Face and contributed by the HF Datasets community

AIME22-24 + AIME25-PartI + AIME25-PartII

justus27/aime-25-genesys dataset hosted on Hugging Face and contributed by the HF Datasets community

jdchang/distill-r1-qwen-1.5b-aime-25-budget dataset hosted on Hugging Face and contributed by the HF Datasets community

jdchang/distill-r1-qwen-1.5b-aime-25-4096 dataset hosted on Hugging Face and contributed by the HF Datasets community

kaiwenw/distill-r1-qwen-1.5b-aime-25-4096-with-old-prm-indices_84480_92160 dataset hosted on Hugging Face and contributed by the HF Datasets community

o3-2025-04-16 Evaluation Results

Precomputed model outputs for evaluation.

  Evaluation Results





  Summary

Metric AIME25 LiveCodeBenchv5 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo HLE

Accuracy 70.3 66.8 97.5 86.0 38.2 86.2 80.0 79.2 35.2 22.8

  AIME25

Average Accuracy: 70.3% ± 1.7% Number of Runs: 10

Run Accuracy Questions Solved Total Questions

1 70.0% 21 30

2 70.0% 21 30

3 70.0% 21 30

4 63.3% 19… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/o3-2025-04-16_eval_5ed6.

gpt-4.1-2025-04-14 Evaluation Results

Precomputed model outputs for evaluation.

  Evaluation Results





  Summary

Metric AIME25 LiveCodeBenchv5 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo HLE AIME24

Accuracy 33.0 46.6 83.2 83.6 30.8 78.3 34.5 65.6 31.1 7.2 0.0

  AIME25

Average Accuracy: 33.0% ± 1.3% Number of Runs: 10

Run Accuracy Questions Solved Total Questions

1 33.3% 10 30

2 33.3% 10 30

3 33.3% 10… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/gpt-4.1-2025-04-14_eval_5ed6.