Benchmarking Google Embeddings 2 against Open-Source Models for Multilingual Dense Retrieval and RAG Systems

Stefano Cirillo, Domenico Desiato, Giuseppe Polese +1

We benchmark Google Embeddings (GE2), a Vertex-AI-hosted bi-encoder with 2,048-token context and explicit task-type conditioning, against five open-source alternatives: BGE-M3, E5-…