# Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini

arXiv: https://arxiv.org/abs/2605.27295 · HTML: https://mlsanity.com/paper/2605.27295/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 45 references that are in the map.
- First posted on arXiv 26 May 2026.

## Builds on (most cited first, 30 of 34)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [Towards Automatic Learning of Procedures from Web Instructional Videos](https://mlsanity.com/paper/1703.09788/) (2017)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research](https://mlsanity.com/paper/1904.03493/) (2019)
- [TextCaps: a Dataset for Image Captioning with Reading Comprehension](https://mlsanity.com/paper/2003.12462/) (2020)
- [Matryoshka Representation Learning](https://mlsanity.com/paper/2205.13147/) (2022)
- [OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement](https://mlsanity.com/paper/2402.14658/) (2024)
- [MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs](https://mlsanity.com/paper/2411.02571/) (2024)
- [DOCCI: Descriptions of Connected and Contrasting Images](https://mlsanity.com/paper/2404.19753/) (2024)
- [MMTEB: Massive Multilingual Text Embedding Benchmark](https://mlsanity.com/paper/2502.13595/) (2025)
- [Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images](https://mlsanity.com/paper/1810.06553/) (2018)
- [Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories](https://mlsanity.com/paper/2306.09224/) (2023)
- [Gemini Embedding: Generalizable Embeddings from Gemini](https://mlsanity.com/paper/2503.07891/) (2025)
- [ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval](https://mlsanity.com/paper/2505.17166/) (2025)
- [CoIR: A Comprehensive Benchmark for Code Information Retrieval Models](https://mlsanity.com/paper/2407.02883/) (2024)
- [MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research](https://mlsanity.com/paper/2503.13399/) (2025)

## Built on by (most cited first, 10 of 10)

- [WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report](https://mlsanity.com/paper/2608.24053/) (2026)
- [The Token Tax of Epistemic Accuracy: Comparing RAG and Long-Context Architectures for Document-Grounded Generative AI Applications](https://mlsanity.com/paper/2606.20898/) (2026)
- [Bridging the Catalog-to-Real Gap: Scalable Product Recognition via Multi-Stage Contrastive Learning](https://mlsanity.com/paper/2607.09888/) (2026)
- [Hierarchical Compression of Vision-Language Model Benchmarks](https://mlsanity.com/paper/2609.37515/) (2026)
- [Learning to Route in Visual Space via Multi-Step Embedding Retrieval](https://mlsanity.com/paper/2609.38743/) (2026)
- [ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research](https://mlsanity.com/paper/2610.02202/) (2026)
- [Learning to Clarify Underspecified Intents Under Limited Interaction](https://mlsanity.com/paper/2610.04719/) (2026)
- [A Testable Theory of Atomic Features](https://mlsanity.com/paper/2610.05794/) (2026)
- [Robota-Embed: Unified VLA Embeddings for Robot In-Context Learning and Evolution](https://mlsanity.com/paper/2610.19495/) (2026)
- [Price of Anarchy of First-Price Auctions in Agentic Markets](https://mlsanity.com/paper/2610.20587/) (2026)

## Abstract (arXiv)

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.