Sabi'a-3 Technical Report

This report presents Sabi'a-3, our new flagship language model, and Sabiazinho-3, a more cost-effective sibling. The models were trained on a large brazilian-centric corpus. Evaluations across diverse professional and academic benchmarks show a strong performance on Portuguese and Brazil-related tasks. Sabi'a-3 shows large improvements in comparison to our previous best of model, Sabia-2 Medium, especially in reasoning-intensive tasks. Notably, Sabi'a-3's average performance matches frontier LLMs, while it is offered at a three to four times lower cost per token, reinforcing the benefits of domain specialization.