ModelBeat
Models/Gemini 2.5 Flash
All models
G

Google DeepMind: Gemini 2.5 Flash

google/gemini-2.5-flash

Gemini 2.5 Flash is Google DeepMind’s proprietary AI model, released Sep 25, 2025. It costs $0.30/M input and $2.50/M output tokens, and handles a 1M-token context window.

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks.

Context
1M
Input
$0.30 / 1M
Output
$2.50 / 1M
Released
Sep 25, 2025
Modalities
fileimagetextaudiovideotext

Benchmarks

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

15.0
Intelligence Index
Epoch AI
15th percentile of tracked models
21.0
Coding Index
Epoch AI
21st percentile of tracked models
4.0
Agentic Index
Epoch AI
4th percentile of tracked models

Reasoning

7 evals
ARC-AGI33.3%

Abstract visual reasoning

ARC-AGI-22.5%

Harder abstract reasoning

GPQA Diamond79.0%

Graduate-level scientific reasoning

Humanity's Last Exam12.1%

Frontier of human expert knowledge

MMLU-Pro83.2%

Broad expert knowledge

SimpleBench41.2%

Common-sense trick questions

WeirdML41.9%

Novel ML problem-solving

Coding

2 evals
LiveCodeBench69.5%

Contamination-free coding

SciCode39.4%

Scientific research coding

Math

3 evals
AIME 2024/202573.1%

Olympiad-qualifier math

FrontierMath4.8%

Research-level math problems

FrontierMath Tier 44.2%

Hardest research math

Agentic & Tools

3 evals
APEX1.8%

Multi-step agentic tasks

Terminal-Bench17.1%

Command-line agentic tasks

τ²-bench31.6%

Tool-agent-user reliability

In the news

2

Compare Gemini 2.5 Flash with

Frequently asked questions

What is Gemini 2.5 Flash?

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks.

Who created Gemini 2.5 Flash?

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

How much does Gemini 2.5 Flash cost?

Gemini 2.5 Flash's list price from Google DeepMind is $0.30 per million input tokens and $2.50 per million output tokens.

What is Gemini 2.5 Flash's context window?

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

How does Gemini 2.5 Flash perform on benchmarks?

On standardized evaluations tracked by Epoch AI, Gemini 2.5 Flash scores 83.2% on MMLU-Pro, 39.4% on SciCode, 4.2% on FrontierMath Tier 4.

Is Gemini 2.5 Flash open source?

Gemini 2.5 Flash 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.