fingertap/GPQA-Diamond dataset hosted on Hugging Face and contributed by the HF Datasets community

Dataset Card for GPQA

GPQA is a multiple-choice, Q&A dataset of very hard questions written and validated by experts in biology, physics, and chemistry. When attempting questions out of their own domain (e.g., a physicist answers a chemistry question), these experts get only 34% accuracy, despite spending >30m with full access to Google. We request that you do not reveal examples from this dataset in plain text or images online, to reduce the risk of leakage into foundation model… See the full description on the dataset page: https://huggingface.co/datasets/Idavidrein/gpqa.

GPQA Diamond Dataset

This dataset contains filtered JSONL files of human annotations on question specificity, answer uniqueness, answer matching to the ground truth for different models for the GPQA Diamond dataset.

The dataset was annotated by two human graders. It contains 198 (original size) * 2 = 396 rows as each rows is repeated twice (one for each human). A human grader given the question, actual answer and model response, has to answer whether the response matches the… See the full description on the dataset page: https://huggingface.co/datasets/nikhilchandak/gpqa-diamond-annotations.

GPQA-Diamond Dataset

Generated by Llama-3.1-8B-InstructDataset: GPQA-Diamond

  Usage

from datasets import load_dataset

Load entire dataset

dataset = load_dataset("dongboklee/GPQA-diamond")["train"]

YukinoshitaYukino/GPQA-Diamond dataset hosted on Hugging Face and contributed by the HF Datasets community

shash42/GPQA-Diamond-Verify dataset hosted on Hugging Face and contributed by the HF Datasets community

Wilson-Lee/tts-embed-dataset-gpqa-diamond dataset hosted on Hugging Face and contributed by the HF Datasets community

yulia-volkova/gpqa-diamond-base-summary-8192-mt dataset hosted on Hugging Face and contributed by the HF Datasets community

yulia-volkova/gpqa-diamond-cue-long-8192-mt dataset hosted on Hugging Face and contributed by the HF Datasets community

adrilmanurung/gpqa-diamond-scrambled-high dataset hosted on Hugging Face and contributed by the HF Datasets community

drproduck/r1-qwen7b-gpqa-diamond-n128 dataset hosted on Hugging Face and contributed by the HF Datasets community

lvogel123/gpqa-diamond-gpt-5-high dataset hosted on Hugging Face and contributed by the HF Datasets community

dongboklee/GPQA-diamond-SmolLM3-3B dataset hosted on Hugging Face and contributed by the HF Datasets community

dongboklee/GPQA-diamond-Llama-3.1-8B-Instruct dataset hosted on Hugging Face and contributed by the HF Datasets community

adrilmanurung/gpqa-diamond-scrambled-low dataset hosted on Hugging Face and contributed by the HF Datasets community

dongboklee/GPQA-diamond-gemma-2-9b-it dataset hosted on Hugging Face and contributed by the HF Datasets community

elichen-skymizer/qwen3-4b-thinking-2507-gpqa-diamond-sampling dataset hosted on Hugging Face and contributed by the HF Datasets community

lvogel123/gpqa-diamond-qwen3-235b-a22b-2507 dataset hosted on Hugging Face and contributed by the HF Datasets community

dongboklee/GPQA-diamond-Qwen2.5-7B-Instruct dataset hosted on Hugging Face and contributed by the HF Datasets community

lvogel123/gpqa-diamond-glm-4.6 dataset hosted on Hugging Face and contributed by the HF Datasets community