Home › Benchmarks › MTEB
MTEB
Benchmark
Capability
The embedding leaderboard behind every retrieval stack.
You're looking at a benchmark record: a test the industry uses to measure chips or models — and what it actually tells you.
The Massive Text Embedding Benchmark scores embedding models across retrieval, clustering and classification — the reference for choosing the vectors under RAG systems, hosted live on Hugging Face.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Sources
Record reviewed as of 2026-01-15 — see Methodology.