---
title: MTEB(por) Leaderboard
emoji: 🏆
colorFrom: green
colorTo: yellow
sdk: static
pinned: true
license: apache-2.0
short_description: Massive Text Embedding Benchmark for Brazilian Portuguese
tags:
- leaderboard
- benchmark
- embeddings
- portuguese
- brazilian-portuguese
- mteb
- retrieval
- sentence-transformers
datasets:
- MTEB-BR/mteb-pt-results
models:
- Alibaba-NLP/gte-Qwen2-1.5B-instruct
- Alibaba-NLP/gte-Qwen2-7B-instruct
- BAAI/bge-m3
- BAAI/bge-small-en-v1.5
- BidirLM/BidirLM-0.6B-Embedding
- BidirLM/BidirLM-1.7B-Embedding
- BidirLM/BidirLM-1B-Embedding
- ICT-TIME-and-Querit/BOOM_4B_v1
- Linq-AI-Research/Linq-Embed-Mistral
- MTEB-BR/baseline-random-encoder
- Mihaiii/Ivysaur
- Octen/Octen-Embedding-0.6B
- Octen/Octen-Embedding-8B
- PORTULAN/albertina-900m-portuguese-ptbr-encoder
- PORTULAN/serafim-100m-portuguese-pt-sentence-encoder
- PORTULAN/serafim-100m-portuguese-pt-sentence-encoder-ir
- PORTULAN/serafim-335m-portuguese-pt-sentence-encoder
- PORTULAN/serafim-335m-portuguese-pt-sentence-encoder-ir
- PORTULAN/serafim-900m-portuguese-pt-sentence-encoder
- PORTULAN/serafim-900m-portuguese-pt-sentence-encoder-ir
- Qwen/Qwen3-Embedding-0.6B
- Qwen/Qwen3-Embedding-4B
- Qwen/Qwen3-Embedding-8B
- Salesforce/SFR-Embedding-2_R
- Salesforce/SFR-Embedding-Mistral
- SamilPwC-AXNode-GenAI/PwC-Embedding_expr
- Snowflake/snowflake-arctic-embed-l-v2.0
- avsolatorio/GIST-all-MiniLM-L6-v2
- avsolatorio/NoInstruct-small-Embedding-v0
- codefuse-ai/F2LLM-0.6B
- codefuse-ai/F2LLM-v2-0.6B
- codefuse-ai/F2LLM-v2-1.7B
- codefuse-ai/F2LLM-v2-14B
- codefuse-ai/F2LLM-v2-160M
- codefuse-ai/F2LLM-v2-330M
- codefuse-ai/F2LLM-v2-4B
- codefuse-ai/F2LLM-v2-80M
- codefuse-ai/F2LLM-v2-8B
- google/embeddinggemma-300m
- ibm-granite/granite-embedding-107m-multilingual
- ibm-granite/granite-embedding-311m-multilingual-r2
- ibm-granite/granite-embedding-97m-multilingual-r2
- intfloat/e5-mistral-7b-instruct
- intfloat/e5-small-v2
- intfloat/multilingual-e5-base
- intfloat/multilingual-e5-large
- intfloat/multilingual-e5-large-instruct
- intfloat/multilingual-e5-small
- jinaai/jina-embeddings-v5-text-small
- lfcc/medlink-bi-encoder
- microsoft/harrier-oss-v1-0.6b
- microsoft/harrier-oss-v1-270m
- microsoft/harrier-oss-v1-27b
- mixedbread-ai/mxbai-embed-large-v1
- neuralmind/bert-base-portuguese-cased
- neuralmind/bert-large-portuguese-cased
- nvidia/llama-embed-nemotron-8b
- rufimelo/Legal-BERTimbau-sts-large
- rufimelo/Legal-BERTimbau-sts-large-ma-v3
- sentence-transformers/LaBSE
- sentence-transformers/all-MiniLM-L12-v2
- sentence-transformers/all-MiniLM-L6-v2
- sentence-transformers/all-mpnet-base-v2
- sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
- sentence-transformers/paraphrase-multilingual-mpnet-base-v2
- stjiris/bert-large-portuguese-cased-legal-mlm-mkd-nli-sts-v1
- stjiris/bert-large-portuguese-cased-legal-mlm-sts-v1.0
- stjiris/bert-large-portuguese-cased-legal-tsdae-gpl-nli-sts-MetaKD-v0
- tardellirs/brazembed-pt-br
- telepix/PIXIE-Rune-v1.0
- tencent/KaLM-Embedding-Gemma3-12B-2511
- thenlper/gte-small
- ufca-llms/Qwen3-Embedding-0.6B-jua-V2
- ufca-llms/jua-4B-legal-only
- ufca-llms/jua-4B-mixed
- ulysses-camara/legal-bert-pt-br
---

# MTEB(por) — Brazilian Portuguese Massive Text Embedding Benchmark

A Massive Text Embedding Benchmark for **Brazilian Portuguese**.

- **93 models** evaluated on **22 native PT-BR tasks** (no machine-translated mMARCO/mkqa)
- Tasks: classification, NLI, STS, clustering, retrieval (incl. Quati Pool), reranking
- Headline metric: **mean_22** (average across all 22 tasks)
- All raw results: [MTEB-BR/mteb-pt-results](https://huggingface.co/datasets/MTEB-BR/mteb-pt-results)
- Source code: [github.com/tardellirs/mteb-br](https://github.com/tardellirs/mteb-br)

## Tasks (16)

| Category | Tasks |
|---|---|
| Classification | HateBR, OffComBR, TweetSentBR, ToxSynPT |
| Pair classification (NLI) | AssinRTE, InferBR |
| STS | AssinSTS |
| Clustering | MedPTClustering, WikipediaPTCategoriesClusteringP2P |
| Retrieval | Quati (Pool), JurisTCU, BRTaxQAR, FaQuADIR, MedPTRetrieval |
| Reranking | QuatiReranking, JurisTCUReranking |

## How to add a model

Submit via GitHub Issues at [tardellirs/mteb-br/issues](https://github.com/tardellirs/mteb-br/issues)
with model_id, eval JSONs, and reproduction script.

## Citation

```bibtex
@misc{mteb-por-2026,
  title  = {MTEB(por): The Brazilian Portuguese MTEB Sub-Benchmark},
  author = {Tardelli, R.S.},
  year   = {2026},
  url    = {https://huggingface.co/spaces/MTEB-BR/leaderboard}
}
```