In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

Design tasks are notoriously difficult, because success is defined by the perception of the target audience, whose feedback is usually not available during design stages. Commonly, design is performed by professionals who have specific domain knowledge (i.e., an intuitive understanding of the implicit requirements of the task) and do not need the feedback of the perception of the viewers during the process. In this paper, we present a novel design methodology for creating minimal sketches of objects that uses an iterative optimization scheme. We define minimality for a sketch via the minimal number of straight line segments required for correct recognition by 75% of naiive viewers. Crowd-sourcing techniques allow us to directly include the perception of the audience in the design process. By joining designers and crowds, we are able to create a human computation system that can efficiently optimize sketches without requiring high levels of domain knowledge (i.e., design skills) from any worker.