Datasets › MetaEval

MetaEval

Introduced by Damien Sileo et al. in Analysis and Prediction of NLP Models Via Task Embeddings10 Dec 2021 archive 2025-07-28

MetaEval is a collection of 101 NLP tasks. It consists of 101 tasks in a benchmark that can be used for future probing and transfer learning.

Benchmarks archive 2025-07-28

No leaderboard in the archive resolves to this dataset.

No paper in the archive has a leaderboard row on this dataset; the archive counts 1 paper for it but never published that list.

No loader listed in the archive.

No task tagged in the archive.

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections