- h
gpqa
- huggingface.co
Updated Jan 15, 2025
Share
Facebook
Twitter
EmailClick to copy linkLink copiedCiteFanqi Wan (2025). gpqa [Dataset]. https://huggingface.co/datasets/Wanfq/gpqaCroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.Dataset updatedJan 15, 2025AuthorsFanqi WanLicenseAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automaticallyDescriptionDataset 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/Wanfq/gpqa.
- h
gpqa
- huggingface.co
- opendatalab.com
Updated Nov 21, 2023ShareFacebookTwitterEmailClick to copy linkLink copiedCiteDavid Rein (2023). gpqa [Dataset]. https://huggingface.co/datasets/Idavidrein/gpqaDataset updatedNov 21, 2023AuthorsDavid ReinLicenseAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automaticallyDescriptionDataset 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.
- h
acc_rd_s1-gpqa
- huggingface.co
Updated Jan 15, 2025ShareFacebookTwitterEmailClick to copy linkLink copiedCiteStewart Slocum (2025). acc_rd_s1-gpqa [Dataset]. https://huggingface.co/datasets/stewy33/acc_rd_s1-gpqaCroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.Dataset updatedJan 15, 2025AuthorsStewart SlocumLicenseAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automaticallyDescriptionDataset 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/stewy33/acc_rd_s1-gpqa.
Not seeing a result you expected?
Learn how you can add new datasets to our index.
FacebookTwitterEmailAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
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/Wanfq/gpqa.