ModelBeat
Models/Gemini 2.5 Flash-Lite
All models
G

Google DeepMind: Gemini 2.5 Flash-Lite

google/gemini-2.5-flash-lite

Gemini 2.5 Flash-Lite is Google DeepMind’s proprietary AI model, released Sep 25, 2025. It costs $0.10/M input and $0.40/M output tokens, and handles a 1M-token context window.

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency.

Context
1M
Input
$0.10 / 1M
Output
$0.40 / 1M
Released
Sep 25, 2025
Modalities
textimagefileaudiovideotext

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Gemini 2.5 Flash-Lite lands among all models tracked on Model Beat.

4.0
Intelligence Index
Epoch AI
4th percentile of tracked models
6.0
Coding Index
Epoch AI
6th percentile of tracked models
0.0
Agentic Index
Epoch AI
0th percentile of tracked models

Reasoning

4 evals
GPQA Diamond62.5%

Graduate-level scientific reasoning

Humanity's Last Exam6.4%

Frontier of human expert knowledge

MMLU-Pro75.9%

Broad expert knowledge

WeirdML35.2%

Novel ML problem-solving

Coding

2 evals
LiveCodeBench59.3%

Contamination-free coding

SciCode19.3%

Scientific research coding

Math

1 evals
AIME 2024/202553.3%

Olympiad-qualifier math

Agentic & Tools

1 evals
τ²-bench18.4%

Tool-agent-user reliability

In the news

1

Compare Gemini 2.5 Flash-Lite with

Frequently asked questions

What is Gemini 2.5 Flash-Lite?

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency.

Who created Gemini 2.5 Flash-Lite?

Gemini 2.5 Flash-Lite is an AI model developed by Google DeepMind, part of the Gemini family, released Sep 25, 2025.

How much does Gemini 2.5 Flash-Lite cost?

Gemini 2.5 Flash-Lite's list price from Google DeepMind is $0.10 per million input tokens and $0.40 per million output tokens.

What is Gemini 2.5 Flash-Lite's context window?

Gemini 2.5 Flash-Lite supports a context window of up to 1M tokens.

How does Gemini 2.5 Flash-Lite perform on benchmarks?

On standardized evaluations tracked by Epoch AI, Gemini 2.5 Flash-Lite scores 59.3% on LiveCodeBench, 75.9% on MMLU-Pro, 6.4% on Humanity's Last Exam.

Is Gemini 2.5 Flash-Lite open source?

Gemini 2.5 Flash-Lite is a proprietary model (API access), available through its provider's API rather than as a downloadable open-weight model.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Jul 30, 2026.