Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
This work provides a single, general-purpose multimodal embedding model that outperforms specialized models across diverse retrieval tasks, benefiting practitioners in search, recommendation, and RAG systems.
Gemini Embedding 2 is a native multimodal embedding model that unifies video, audio, image, and text in a single representation space, achieving state-of-the-art results on benchmarks like MSCOCO (62.9 R@1), Vatex (68.8 NDCG@10), MTEB multilingual (69.9), and MTEB Code (84.0), surpassing specialized models.
We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified representation space. We leverage the multimodal capabilities of Gemini to produce embeddings for arbitrary combinations of interleaved inputs across all these modalities that generalize well across a wide variety of tasks. Applying large-scale contrastive learning in a multi-task multi-stage training setup, we achieve state-of-the-art performance on key embedding benchmarks including unimodal, cross-modal, and multimodal retrieval spanning a diverse set of tasks. We show that our embedding model demonstrates strong performance (with a score of 62.9 R@1 on MSCOCO, 68.8 NDCG@10 on Vatex, 69.9 on MTEB multilingual and 84.0 on MTEB Code) across a variety of tasks surpassing the performance of specialized models. These unified capabilities make Gemini Embedding 2 a promising candidate for downstream use cases such as RAG, recommendation and search. Furthermore, its robust zero-shot performance across distinct fields - from astronomy and bioscience to fine arts and the culinary arts - establishes it as a highly reliable, out-of-the-box representation even for specialized domains.