embeddings-benchmark/mteb

MTEB: Massive Text Embedding Benchmark

86
/ 100
Verified

This tool helps machine learning engineers and researchers assess the quality and performance of different text embedding models. You provide a text embedding model and specific evaluation tasks (like text classification or retrieval). The output is a clear set of metrics showing how well the model performs on those tasks, allowing for informed comparison and selection of the best model.

3,159 stars. Used by 6 other packages. Actively maintained with 107 commits in the last 30 days. Available on PyPI.

Use this if you need to systematically compare and evaluate multiple text embedding models against standardized benchmarks to choose the most effective one for your application.

Not ideal if you are looking for a tool to train new text embedding models or to apply embeddings directly in a production system without prior evaluation.

natural-language-processing model-evaluation text-embeddings information-retrieval machine-learning-research
Maintenance 22 / 25
Adoption 15 / 25
Maturity 25 / 25
Community 24 / 25

How are scores calculated?

Stars

3,159

Forks

568

Language

Python

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

107

Dependencies

13

Reverse dependents

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/embeddings-benchmark/mteb"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.