datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
super_glue
Dataset Card for "super_glue"
Dataset Summary
SuperGLUE (https://super.gluebenchmark.com/) is a new benchmark styled after
GLUE with a new set of more difficult language understanding tasks, improved
resources, and a new public leaderboard.
Supported Tasks and Leaderboards
More Information Needed
Languages
More Information Needed
Dataset Structure
Data Instances
axb
Size of downloaded dataset files: 0.03 MB
Size of… See the full description on the dataset page: https://huggingface.co/datasets/aps/super_glue.superglue_wsc_raw
Winograd Schema Challenge examples included in the SuperGLUE Benchmark
Specifically: The wsc and wsc.fixed datasets from the HuggingFace "super_glue" repository.
Data Fields
text (str): The text of the schema.
span1_index (int): Starting word index of first entity.
span2_index (int): Starting word index of second entity.
span1_text (str): Textual representation of first entity.
span2_text (str): Textual representation of second entity.
idx (int): Index of the example in… See the full description on the dataset page: https://huggingface.co/datasets/coref-data/superglue_wsc_raw.super_glue-copa
Dataset Card for "super_glue-copa"
More Information needed
Note: This dataset was utilized for the evaluation of probability-based prompt selection techniques in the paper 'Improving Probability-based Prompt Selection Through Unified Evaluation and Analysis'. It differs from the actual benchmark dataset.
super_glue_wsc.fixed_promptsourcesuper_glue_record_promptsourcesuper_glue_copa_promptsourcesuperglue
SuperGLUE Benchmark Datasets
This repository contains the SuperGLUE benchmark datasets. Each dataset is available as a separate configuration, making it easy to load individual datasets using the datasets library.
Dataset Descriptions
Datasets Included
BoolQ: A question-answering task where each example consists of a short passage and a yes/no question about the passage. The questions are provided anonymously and unsolicited by users of the Google search… See the full description on the dataset page: https://huggingface.co/datasets/Hyukkyu/superglue.task1393_superglue_copa_text_completion
Dataset Card for Natural Instructions (https://github.com/allenai/natural-instructions) Task: task1393_superglue_copa_text_completion
Additional Information
Citation Information
The following paper introduces the corpus in detail. If you use the corpus in published work, please cite it:
@misc{wang2022supernaturalinstructionsgeneralizationdeclarativeinstructions,
title={Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP… See the full description on the dataset page: https://huggingface.co/datasets/Lots-of-LoRAs/task1393_superglue_copa_text_completion.superglue_wsc_indiscrimThis dataset was generated by reformatting coref-data/superglue_wsc_raw into the indiscrim coreference format. See that repo for dataset details.
See ianporada/coref-data for additional conversion details and the conversion script.
Please create an issue in the repo above or in this dataset repo for any questions.
super_glue_boolq_promptsourceSuperGLUE_COPA
SuperGLUE_COPA — evaluation data (OpenCompass format)
Bud Ecosystem eval mirror (config SuperGLUE_COPA_gen); COPA from SuperGLUE (BSD-2-Clause), unchanged.
superglue-hr
BalkanBench SuperGLUE - Croatian
Part of BalkanBench - the open, reproducible
benchmark for language models across Serbian, Croatian, Montenegrin, and
Bosnian (BCMS). Live leaderboard at https://balkanbench.com/leaderboard.
Background: Release of BalkanBench - the vision behind it
(Medium, 2026-04-27).
This is the Croatian SuperGLUE released preview track of BalkanBench v0.1.
Croatian publishes alongside Serbian (the official frozen track) and
Montenegrin as a 5-task preview:… See the full description on the dataset page: https://huggingface.co/datasets/permitt/superglue-hr.super_glue_multirc_promptsourcesuperglue-mne
BalkanBench SuperGLUE - Montenegrin
Part of BalkanBench - the open, reproducible
benchmark for language models across Serbian, Croatian, Montenegrin, and
Bosnian (BCMS). Live leaderboard at https://balkanbench.com/leaderboard.
Background: Release of BalkanBench - the vision behind it
(Medium, 2026-04-27).
This is the Montenegrin SuperGLUE released preview track of BalkanBench
v0.1, covering the same 5 ranked tasks as the Croatian preview. Same
scoring contract as Serbian (the… See the full description on the dataset page: https://huggingface.co/datasets/permitt/superglue-mne.super_glue_recordsuper_glue-ka
super_glue-ka
Georgian translation of the SuperGLUE benchmark suite.
Dataset Summary
Property
Value
Languages
Georgian, English
Task
Natural Language Understanding
Configs
Multiple SuperGLUE tasks available as separate configs.
Translation Methodology
Translation model generates initial Georgian translation
Human contractor verifies and fixes translation if needed
Human validator confirms translation quality… See the full description on the dataset page: https://huggingface.co/datasets/tbilisi-ai-lab/super_glue-ka.super_glue_cb_promptsourcesuperglue-sr
BalkanBench SuperGLUE - Serbian
Part of BalkanBench - the open, reproducible
benchmark for language models across Serbian, Croatian, Montenegrin, and
Bosnian (BCMS). Live leaderboard at https://balkanbench.com/leaderboard.
Background and motivation: Release of BalkanBench - the vision behind it
(Medium, 2026-04-27).
This is the Serbian SuperGLUE track of BalkanBench v0.1. Serbian is the
official frozen track: the leaderboard's ranked average is computed over
6 ranked tasks… See the full description on the dataset page: https://huggingface.co/datasets/permitt/superglue-sr.ru_superglue_formattedsuper_glue_rte_promptsourceSuperGLUE_BoolQ
SuperGLUE_BoolQ — eval data (OpenCompass format)
Bud Ecosystem eval mirror (config SuperGLUE_BoolQ_gen); BoolQ from SuperGLUE, CC-BY-SA-3.0 (share-alike), unchanged.
super_glue_wic_promptsourcesuperglue_record
ReCoRD — evaluation data (OpenCompass format)
Bud Ecosystem eval mirror. OpenCompass-native eval data for ReCoRD, laid out at SuperGLUE/ReCoRD/ exactly as the OpenCompass dataset loader expects. Sourced from the OpenCompass data distribution; license CC-BY-4.0, unchanged; all rights remain with the original authors.
superglue_wsc
WSC — evaluation data (OpenCompass format)
Bud Ecosystem eval mirror. OpenCompass-native eval data for WSC, laid out at SuperGLUE/WSC/ exactly as the OpenCompass dataset loader expects. Sourced from the OpenCompass data distribution; license CC-BY-4.0, unchanged; all rights remain with the original authors.
super_glue-cb
Dataset Card for "super_glue-cb"
More Information needed
Note: This dataset was utilized for the evaluation of probability-based prompt selection techniques in the paper 'Improving Probability-based Prompt Selection Through Unified Evaluation and Analysis'. It differs from the actual benchmark dataset.
superglue_rte
RTE — evaluation data (OpenCompass format)
Bud Ecosystem eval mirror. OpenCompass-native eval data for RTE, laid out at SuperGLUE/RTE/ exactly as the OpenCompass dataset loader expects. Sourced from the OpenCompass data distribution; license CC-BY-4.0, unchanged; all rights remain with the original authors.
superglue_wic
WiC — evaluation data (OpenCompass format)
Bud Ecosystem eval mirror. OpenCompass-native eval data for WiC, laid out at SuperGLUE/WiC/ exactly as the OpenCompass dataset loader expects. Sourced from the OpenCompass data distribution; license CC-BY-4.0, unchanged; all rights remain with the original authors.
superglue_copa_eval_multireprautoeval-eval-jeffdshen__inverse_superglue_mixedp1-jeffdshen__inverse-63643c-1665558894
Dataset Card for AutoTrain Evaluator
This repository contains model predictions generated by AutoTrain for the following task and dataset:
Task: Zero-Shot Text Classification
Model: facebook/opt-6.7b
Dataset: jeffdshen/inverse_superglue_mixedp1
Config: jeffdshen--inverse_superglue_mixedp1
Split: train
To run new evaluation jobs, visit Hugging Face's automatic model evaluator.
Contributions
Thanks to @jeffdshen for evaluating this model.
bigbench-superglue-tsi
Dataset Card for "bigbench-superglue-tsi"
More Information needed