GLUE (General Language Understanding Evaluation benchmark)

Dataset Card for GLUE

Open

Publisher: New York University
License: unknown
Published: May 2026
Canonical: huggingface.co/datasets/nyu-mll/glue

Cite

Notes

Only stored in your browser.

Sample tasks

from the eval dataset

premise

The cat sat on the mat.

hypothesis

The cat did not sit on the mat.

label

-1

idx0

Show 4 more examples

premise

The cat did not sit on the mat.

hypothesis

The cat sat on the mat.

label

-1

idx1

premise

When you've got no snow, it's really hard to learn a snow sport so we looked at all the different ways I could mimic being on snow without actually being on snow.

hypothesis

When you've got snow, it's really hard to learn a snow sport so we looked at all the different ways I could mimic being on snow without actually being on snow.

label

-1

idx2

premise

When you've got snow, it's really hard to learn a snow sport so we looked at all the different ways I could mimic being on snow without actually being on snow.

hypothesis

When you've got no snow, it's really hard to learn a snow sport so we looked at all the different ways I could mimic being on snow without actually being on snow.

label

-1

idx3

premise

Out of the box, Ouya supports media apps such as Twitch.tv and XBMC media player.

hypothesis

Out of the box, Ouya doesn't support media apps such as Twitch.tv and XBMC media player.

label

-1

idx4

[
  {
    "premise": "The cat sat on the mat.",
    "hypothesis": "The cat did not sit on the mat.",
    "label": -1,
    "idx": 0
  },
  {
    "premise": "The cat did not sit on the mat.",
    "hypothesis": "The cat sat on the mat.",
    "label": -1,
    "idx": 1
  },
  {
    "premise": "When you've got no snow, it's really hard to learn a snow sport so we looked at all the different ways I could mimic being on snow without actually being on snow.",
    "hypothesis": "When you've got snow, it's really hard to learn a snow sport so we looked at all the different ways I could mimic being on snow without actually being on snow.",
    "label": -1,
    "idx": 2
  },
  {
    "premise": "When you've got snow, it's really hard to learn a snow sport so we looked at all the different ways I could mimic being on snow without actually being on snow.",
    "hypothesis": "When you've got no snow, it's really hard to learn a snow sport so we looked at all the different ways I could mimic being on snow without actually being on snow.",
    "label": -1,
    "idx": 3
  },
  {
    "premise": "Out of the box, Ouya supports media apps such as Twitch.tv and XBMC media player.",
    "hypothesis": "Out of the box, Ouya doesn't support media apps such as Twitch.tv and XBMC media player.",
    "label": -1,
    "idx": 4
  }
]

FAQ

What is GLUE (General Language Understanding Evaluation benchmark)?: Dataset Card for GLUE
What license is GLUE (General Language Understanding Evaluation benchmark) under?: GLUE (General Language Understanding Evaluation benchmark) is available under unknown.