Gemini: A Family of Highly Capable Multimodal Models
Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu + 1346 more
TLDR
Gemini is a new family of multimodal AI models excelling in image, audio, video, and text understanding, achieving state-of-the-art results across numerous benchmarks including human-expert level on MMLU.
Key contributions
- Introduces Gemini models in Ultra, Pro, and Nano sizes tailored for diverse applications from complex reasoning to on-device use.
- Gemini Ultra achieves state-of-the-art performance on 30 out of 32 benchmarks, including first human-expert level on MMLU exam.
- Demonstrates significant improvements across 20 multimodal benchmarks, highlighting advanced cross-modal reasoning and language understanding.
Why it matters
This paper matters because it presents a versatile and highly capable multimodal model family that pushes the boundaries of AI understanding across multiple data types, enabling more sophisticated and practical applications in real-world scenarios. By achieving unprecedented benchmark results and supporting responsible deployment, Gemini sets a new standard for multimodal AI systems.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.