Retrieval, embeddings and long context
MTEB / MMTEB
Embedding quality across retrieval, similarity, classification and multilingual tasks.
About MTEB / MMTEB
What it measures
Task-specific metrics; report retrieval nDCG separately from broad averages.
Scope & limitations
Vector databases should benchmark a declared embedding-plus-index pipeline; MTEB is not itself a database performance test.
Evaluation environment
Embedding/reranking endpoint through the selected MTEB task collection.