mteb-bucc-5-languages

IN premise — summaries/2026/08/24/muennighoff-2022-mteb-sR-references-chunk-2.md

Created 2026-08-25T02:58:23+00:00

BUCC in MTEB supports exactly 5 languages: EN, FR, RU, DE, ZH.

Summary

The BUCC benchmark in MTEB only evaluates cross-lingual text matching across five languages (English, French, Russian, German, and Chinese), so any conclusions about multilingual performance drawn from it are limited to that set and tell you nothing about how a system behaves on other languages.