Cohere Labs: data mixing lifts 3.35B model to 93%+ in-language reasoning across 60 languages

Cohere_Labs · x · 2026-09-11

Cohere Labs released "Building Multilingual Bridges," a data-centric study on enabling LLMs to reason in the user's language (L2 reasoning) instead of defaulting to English. Their 3.35B Tiny Aya L2-Thinker achieves >93% in-language reasoning across 60 languages on 6 benchmarks. Key findings: generalization to held-out languages requires broad language coverage, readily available multilingual non-reasoning data, and a strong English reasoning backbone.

Related event: Cohere Open-Sources Tiny Aya L2-Thinker, a 3.35B Multilingual Reasoning Model(3 posts)→

Original post →

More from Research

Research channel →