MTEB logo MTEB
Polish icon

Polish

Cite this benchmark

@article{poswiata2024plmteb,
  author = {Rafał Poświata and Sławomir Dadas and Michał Perełkiewicz},
  journal = {arXiv preprint arXiv:2405.10138},
  title = {PL-MTEB: Polish Massive Text Embedding Benchmark},
  year = {2024},
}

Polish text embedding quality across classification, clustering, pair classification, retrieval, and semantic similarity, combining adapted community datasets with a novel Polish scientific literature corpus (PLSC).

Reference paper →
Languages 1
Tasks 17
Task Types 4
Models 0