Gemini: A Family of Highly Capable Multimodal Models

TLDR

The Gemini family comprises Ultra, Pro, and Nano models, designed for tasks from complex reasoning to on‑device, memory‑constrained applications. This report introduces Gemini, a multimodal model family that excels in image, audio, video, and text understanding. The authors outline a responsible post‑training and deployment strategy for Gemini models through services such as Gemini, Gemini Advanced, Google AI Studio, and Cloud Vertex AI. Evaluation shows Gemini Ultra sets new state‑of‑the‑art performance on 30 of 32 benchmarks, becomes the first model to achieve human‑expert accuracy on MMLU, and improves all 20 multimodal benchmarks, with the family’s cross‑modal reasoning and language capabilities poised to enable diverse use cases.

Abstract

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of the Gemini family in cross-modal reasoning and language understanding will enable a wide variety of use cases. We discuss our approach toward post-training and deploying Gemini models responsibly to users through services including Gemini, Gemini Advanced, Google AI Studio, and Cloud Vertex AI.