# MMTEB

MMTEB is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Measures multilingual text embeddings across more than 500 quality-controlled tasks covering over 250 languages.

## Details

- Address: Online, Global
- Website: [github.com/embeddings-benchmark/mteb](<https://github.com/embeddings-benchmark/mteb>)
- Tags: Helpful, Science
- Category: Retrieval
- Status: Active
- Data licence: Apache-2.0
- Data access: open
- Grader: exact
- Organization: MTEB community
- Released: 2025-02
- Paper: [arxiv.org/abs/2502.13595](<https://arxiv.org/abs/2502.13595>)
- Leaderboard: [huggingface.co/spaces/mteb/leaderboard](<https://huggingface.co/spaces/mteb/leaderboard>)
- Repository: [github.com/embeddings-benchmark/mteb](<https://github.com/embeddings-benchmark/mteb>)
- Task count: 500
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is MMTEB?

MMTEB is at Online, Global.

### How do I contact MMTEB?

To contact MMTEB, visit https://github.com/embeddings-benchmark/mteb.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/mmteb>)
- [Retrieval in Online](<https://aibenchmarkindex.com/global/online/category/retrieval.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.