MTEB-BR Benchmark

What is MTEB-BR?

MTEB-BR is a text embedding benchmark for Brazilian Portuguese with 22 native tasks across seven categories, including classification, clustering, retrieval…

Released

2026-07-06

Evaluates

General AI, Information retrieval, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.04581

MTEB-BR paper and code

• Paper https://arxiv.org/abs/2607.04581
• Code https://github.com/tardellirs/mteb-br

Which sources cite MTEB-BR?

• MTEB-BR

Related General AI, Information retrieval, Language & Knowledge, cs.CL benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench