SkMTEB
SkMTEB is the first comprehensive MTEB-style text embedding benchmark for Slovak — a low-resource West Slavic language with ~5 million speakers.
- SlovakNLP Community
Can I use it?
The license also allows commercial use if you credit the authors and specify the license.
About this resource
SkMTEB is the first comprehensive MTEB-style text embedding benchmark for Slovak — a low-resource West Slavic language with ~5 million speakers. The benchmark comprises 31 datasets across 7 task types, covering nearly 4× the depth of existing multilingual benchmark coverage for Slovak (compared to 8 tasks in MMTEB).
The SkMTEB — Slovak Text Embedding Benchmark benchmark uses this dataset.See the leaderboard
See a mistake or a missing detail? Write to us.More resources for this task
All resources for “Search by meaning” (5)- ModelBGE-M3
BGE-M3 is a new embedding model, which is distinguished for its versatility in Multi-Linguality, Multi-Functionality, and Multi-Granularity.
- University of Science and Technology of China
- BAAI
No license specified - ModelE5-sk-large
This is a specialized Slovak sentence-transformers model that maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity,…
MIT - ModelE5-sk-small
This is a specialized Slovak sentence-transformers model that maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity,…
MIT - DatasetSlovak STS Synthetic
This is a synthetic Slovak dataset intended for the semantic textual similarity (STS) task.
CC BY-NC 4.0