Papers
arxiv:2210.07316

MTEB: Massive Text Embedding Benchmark

Published on Oct 13, 2022

Abstract

Text embeddings are commonly evaluated on a small set of datasets from a single task not covering their possible applications to other tasks. It is unclear whether state-of-the-art embeddings on semantic textual similarity (STS) can be equally well applied to other tasks like clustering or reranking. This makes progress in the field difficult to track, as various models are constantly being proposed without proper evaluation. To solve this problem, we introduce the Massive Text Embedding Benchmark (MTEB). MTEB spans 8 embedding tasks covering a total of 58 datasets and 112 languages. Through the benchmarking of 33 models on MTEB, we establish the most comprehensive benchmark of text embeddings to date. We find that no particular text embedding method dominates across all tasks. This suggests that the field has yet to converge on a universal text embedding method and scale it up sufficiently to provide state-of-the-art results on all embedding tasks. MTEB comes with open-source code and a public leaderboard at https://github.com/embeddings-benchmark/mteb.

Community

Paper author

Link to the leaderboard: https://huggingface.co/spaces/mteb/leaderboard πŸ€—

Sign up or log in to comment

Models citing this paper 57

Browse 57 models citing this paper

Datasets citing this paper 1

Spaces citing this paper 245

Collections including this paper 1