The AI Lab at Poland’s National Information Processing Institute (OPI) has developed PolDense, a new family of language models designed specifically for information retrieval. PolDense models have been designed for systems that process large volumes of unstructured data, particularly search engines, chatbots, AI assistants and applications using Retrieval-Augmented Generation (RAG) architecture. PolDense 1B currently ranks first in the public Polish Information Retrieval Benchmark (PIRB) ranking, achieving the highest average score among all models evaluated. The team is also working on EuroDense, a model that will support the most widely used European languages. “The release of the PolDense models is another step towards building Poland’s expertise in artificial intelligence. We are creating open technologies that can be used by researchers, public authorities and businesses to develop modern, efficient and secure AI tools. It is worth emphasising that one of OPI’s new models ranks first in the Polish Information Retrieval Benchmark, outperforming multilingual models such as Llama and BGE,” said Jarosław Protasiewicz, Director of the National Information Processing Institute.