Embeddings & Vector SearchNiklas Muennighoff et al. (Hugging Face, Cohere)Hugging FaceCohere

Hugging Face and Cohere release MTEB

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Released MTEB — 8 tasks, 58 datasets, 112 languages

Why it matters

The common yardstick for the embedding model race. Its key conclusion: no embedding method dominates every task

Source — Primary sources first; secondary reports are labelled “Press”

Paperarxiv.orghttps://arxiv.org/abs/2210.07316

Added in Week 35, 2026 · See that week

On the map — ⑰ Embeddings line

  1. Previous stopDPR
  2. This record · stopMTEB
  3. Next stopPinecone serverless
See it on the map

Same week

US BIS imposes first round of advanced computing export controlsGovernment

Nearby on the same axis

Microsoft researchers present E5PaperOpenAI releases text-embedding-ada-002OfficialKusupati et al. present Matryoshka Representation LearningPaperGoogle DeepMind researchers present SigLIPPaper