# Sabi'a-4 Technical Report

arXiv: https://arxiv.org/abs/2603.10213 · HTML: https://mlsanity.com/paper/2603.10213/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 7 of 7)

- [APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay](https://mlsanity.com/paper/2504.03601/) (2025)
- [Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following](https://mlsanity.com/paper/2410.15553/) (2024)
- [Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries](https://mlsanity.com/paper/2409.12640/) (2024)
- [Automatic Legal Writing Evaluation of LLMs](https://mlsanity.com/paper/2504.21202/) (2025)
- [Building High-Quality Datasets for Portuguese LLMs: From Common Crawl Snapshots to Industrial-Grade Corpora](https://mlsanity.com/paper/2509.08824/) (2025)
- [Juru: Legal Brazilian Large Language Model from Reputable Sources](https://mlsanity.com/paper/2403.18140/) (2024)
- [Comparing Knowledge Injection Methods for LLMs in a Low-Resource Regime](https://mlsanity.com/paper/2508.06178/) (2025)

## Built on by (most cited first, 6 of 6)

- [Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese](https://mlsanity.com/paper/2606.07853/) (2026)
- [CAPITU: A Benchmark for Evaluating Instruction-Following in Brazilian Portuguese with Literary Context](https://mlsanity.com/paper/2603.22576/) (2026)
- [MARCA: A Checklist-Based Benchmark for Multilingual Web Search](https://mlsanity.com/paper/2604.14448/) (2026)
- [BLUEX v2: Benchmarking LLMs on Open-Ended Questions from Brazilian University Entrance Exams](https://mlsanity.com/paper/2606.22723/) (2026)
- [Eleven Years of BRACIS: A Meta-Scientific Study of the Brazilian Conference on Intelligent Systems](https://mlsanity.com/paper/2608.09964/) (2026)
- [Lumen-bench: Cross-Lingual Safety Gaps and the Say-Do Problem in Tool-Calling Large Language Models](https://mlsanity.com/paper/2610.15134/) (2026)

## Abstract (arXiv)

This technical report presents Sabi'a-4 and Sabiazinho-4, a new generation of Portuguese language models with a focus on Brazilian Portuguese language. The models were developed through a four-stage training pipeline: continued pre-training on Portuguese and Brazilian legal corpora, long-context extension to 128K tokens, supervised fine-tuning on instruction data spanning chat, code, legal tasks, and function calling, and preference alignment. We evaluate the models on six benchmark categories: conversational capabilities in Brazilian Portuguese, knowledge of Brazilian legislation, long-context understanding, instruction following, standardized exams, and agentic capabilities including tool use and web navigation. Results show that Sabi'a-4 and Sabiazinho-4 achieve a favorable cost-performance trade-off compared to other models, positioning them in the upper-left region of the pricing-accuracy chart. The models show improvements over previous generations in legal document drafting, multi-turn dialogue quality, and agentic task completion.