MTEB (Massive Text Embedding Benchmark)

A multi-task suite that scores text embedding models on retrieval, classification, clustering, reranking, similarity, summarization and pair classification.

Also known as: Massive Text Embedding Benchmark, MMTEB

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categoryembedding
Subcategorytext embedding
Page statusactive
Directionhigher_is_better
Dataset licenceVaries by dataset (each task keeps its source dataset's own licence); the MTEB benchmark code itself is Apache-2.0.
PublisherHugging Face and Cohere (original authors); maintained today by the open embeddings-benchmark community

What it measures

MTEB measures how useful a text embedding model's output vectors are for downstream work, not how well the model writes text. Each task type applies a fixed, non-learned scoring routine to the embeddings a model produces: nearest-neighbour classification, clustering, cosine-similarity ranking for retrieval and reranking, or correlation with human similarity judgements. The task types in scope for this repository are retrieval, classification, clustering, reranking, semantic textual similarity, summarization and pair classification; bitext mining and the newer image, audio and video MTEB variants sit outside this family page's scope. Coverage ranges from English-only task sets to multilingual ones spanning over 100 languages.

Task format

Varies by task type: query-document ranking for retrieval and reranking, single-text classification into a fixed label set, unsupervised clustering of a text collection, sentence-pair scoring for similarity or entailment, and summary scoring by embedding distance to reference summaries. Every task consumes only the model's embedding vectors.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub