Gemini: A Family of Highly Capable Multimodal Models
This work addresses the problem of multimodal AI capabilities for users needing advanced reasoning and on-device applications, representing a significant advancement rather than an incremental improvement.
The paper introduces the Gemini family of multimodal models, which tackle multimodal understanding across image, audio, video, and text, achieving state-of-the-art results on 30 out of 32 benchmarks, including human-expert performance on MMLU.
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.