Gemini 2.5 Flash Lite

Closed Source

Closed Weights

Parameters

Context Length

1.05M

Modality

Multimodal

Architecture

Dense

License

Proprietary

Release Date

25 Sept 2025

Knowledge Cutoff

Jan 2025

Evaluation Benchmarks

Rank

#40

Benchmark	Score	Rank
Professional Knowledge MMLU Pro	0.79	32
LiveBench Average high LiveBench Average	0.64	61
General Text Text Arena	1380	117

Rankings

Overall Rank

#40

Coding Rank

About Gemini 2.5 Flash Lite

Gemini 2.5 Flash Lite is Google's lightweight Mixture-of-Experts multimodal model optimized for cost-sensitive, high-throughput subagent tasks. It features a configurable thinking budget and native audio/video support over a 1M context window.

Technical Specifications

Detailed architecture specifications are limited for proprietary models.

Resources

Official Documentation Release Notes Read the Paper

About Gemini 2.5

Google's advanced multimodal models with native understanding of text, images, audio, and video. Features massive context windows up to 2.1M tokens, max thinking modes for complex reasoning, and optimized variants for different performance/cost tradeoffs. Includes Pro, Flash, and Flash Lite variants with configurable thinking capabilities for transparent reasoning.