MTEB logo MTEB
Dutch icon

Dutch

Cite this benchmark

@misc{banar2025mtebnle5nlembeddingbenchmark,
  archiveprefix = {arXiv},
  author = {Nikolay Banar and Ehsan Lotfi and Jens Van Nooten and Cristina Arhiliuc and Marija Kliocaite and Walter Daelemans},
  eprint = {22509.12340},
  primaryclass = {cs.CL},
  title = {MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch},
  url = {https://arxiv.org/abs/2509.12340},
  year = {2025},
}

Dutch text embedding quality across classification, clustering, pair classification, multilabel classification, reranking, retrieval, and semantic similarity.

Reference paper →
Languages 1
Tasks 40
Task Types 7
Models 0