Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

TL;DR

Gemini 2.5 models represent a significant advancement in AI, combining state-of-the-art reasoning, multimodal understanding, and long context processing, enabling complex agentic workflows and diverse application scenarios.

Contribution

Introduction of Gemini 2.5 model family with advanced reasoning, multimodality, and long context capabilities, setting new performance standards and offering a range of models balancing capability and cost.

Findings

Gemini 2.5 Pro achieves state-of-the-art performance on reasoning benchmarks.

Gemini 2.5 Pro can process up to 3 hours of video content.

Models span the full Pareto frontier of capability versus cost.

Abstract

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.