QuALITY

Multiple-choice QA over English passages averaging about 5,000 tokens; writers read the full article, and a hard subset beats speed-limited annotators.

Also known as: QuALITY: Question Answering with Long Input Texts, Yes!, QUALITY

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorylong-context
Subcategorylong-document English multiple-choice QA (~5k-token passages, four options)
Page statusactive
Metricaccuracy (all); easy_acc and hard_acc also reported
Directionhigher_is_better
Unit%
Dataset size6737
Dataset licenceCC-BY-4.0
PublisherNew York University (NYU-MLL) and collaborators

What it measures

QuALITY (Question Answering with Long Input Texts, Yes!) gives a model an English article of about 5,000 tokens and a four-option question written by a contributor who read the whole passage. Untimed validators must agree the item is answerable; a hard subset is the slice where speed-limited annotators mostly fail. The skill is long-document comprehension that skimming and lexical overlap do not solve. OpenCompass, the census harness for this id, runs the HTML-stripped development split as a generation multiple-choice task, not the hidden test set used by the NYU leaderboard.

Task format

Four-way multiple choice (A–D) over a long English article plus a question. Official scoring is accuracy on the held-out test set. OpenCompass is zero-shot generation with first_option_postprocess over ABCD.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub