Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

TL;DR

Gemini 1.5 models represent a significant advancement in multimodal understanding, capable of processing millions of tokens for tasks like long-document QA, video, and audio analysis, with high recall and efficiency.

Contribution

Introduction of Gemini 1.5 models, including a high-performance Pro version and a lightweight Flash variant, pushing the limits of long-context multimodal reasoning and retrieval.

Findings

Achieves near-perfect retrieval (>99%) up to 10 million tokens

Sets new state-of-the-art in long-document and long-video QA

Enables practical applications like professional task assistance and language translation

Abstract

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.