MTEB / MMTEB
Embedding quality: 500+ tasks in 250+ languages (retrieval, classification, clustering and more)
v4embeddingsactive
Definition
- Version
- v4
- Category
- embeddings
- Maintainer
- MTEB community (Enevoldsen, Muennighoff et al.), Denmark/intl
- Status
- active
- Home page
- https://huggingface.co/spaces/mteb/leaderboard
Sources
- MMTEB: Massive Multilingual Text Embedding Benchmark arxiv.org https://arxiv.org/abs/2502.13595
- huggingface.co/spaces/mteb/leaderboard https://huggingface.co/spaces/mteb/leaderboard
- GitHub - embeddings-benchmark/mteb: MTEB: State-of-the-art evaluation of embeddings across languages and modalities github.com https://github.com/embeddings-benchmark/mteb
Scores
The notes record no score on this benchmark.
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MTEB / MMTEB", https://aurion.semai.id/benchmarks/mteb/, records of October 2026.