Dataset · nyu-mll
GLUE benchmark for language understanding
nyu-mll/glue
Collection of tasks and data for training and evaluating English text understanding systems.
What's inside
This is a collection of resources for training, evaluating, and analyzing natural language understanding systems. It includes multiple tasks, including a manually prepared evaluation set ax; data in English, with text and tabular modalities. The volume ranges from 1 to 10 million examples, and a public GLUE leaderboard is available.
What you can do with it
- Evaluating and comparing NLU models on a unified benchmark
- Fine-tuning a classifier for one of the GLUE tasks
- Testing language model transfer to English NLU tasks
- Tasks
- Text classification
- Languages
- English
- Size
- 1M–10M rows
- Downloads this month
- 467.2K
- Likes
- 787
Models trained on it
- tasksource/ModernBERT-base-nliZero shot classification 43.8K
- StrandsAgents/strands-decider-2B-qwen3.5-v1-2610Text classification 25K
- chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-GGUFText classification 16K
- StrandsAgents/strands-decider-2B-hobson-v21Text classification 15.3K
- tasksource/deberta-small-long-nliZero shot classification 9.3K
- tasksource/ModernBERT-large-nliZero shot classification 8.5K
- StrandsAgents/strands-decider-2B-hobson-v19Text classification 7K
- tasksource/ettin-17m-embedSentence similarity 5.6K
How to load it
from datasets import load_dataset
ds = load_dataset("nyu-mll/glue")