Gemini 2.5 Flash Preview (09/2025) – Thinking

Same checkpoint with thinking enabled by default for deeper reasoning and stepwise analysis on complex tasks. Routed to Gemini 2.5 Flash Thinking (stable).

Reasoning
Vision
Audio Input
Native PDF input
Tool Calling
Structured Output

Added Sep 25, 2025

Pricing

Auto routing · per 1M tokens

Input: $0.30
Output: $2.50
Cache read: $0.030

Compare provider prices

Specifications

Context window: 1M
Max output: 65.5K

Benchmarks

Artificial Analysis

Vectara

Sourced from Artificial Analysis.

Intelligence Index

15.5

Better than 57% of models compared

Agentic work

T²-Bench Telecom (legacy)

Legacy fallback · Conversational AI agents in dual-control scenarios

45.6%

Better than 49% of models compared

Document reasoning

AA-LCR v1.1

Long context reasoning with updated grading

71.0%

Better than 65% of models compared

Reasoning

HLE

Humanity's Last Exam

13.8%

Better than 60% of models compared

IFBench

Instruction-following benchmark

52.3%

Better than 62% of models compared

Coding

Terminal-Bench Hard (legacy)

Legacy fallback · Agentic coding and terminal use

16.7%

Better than 54% of models compared

LiveCodeBench

Contamination-free coding benchmark

71.3%

Better than 82% of models compared

Math

AIME 2025

American Invitational Mathematics Examination 2025

78.3%

Better than 73% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

84.2%

Better than 88% of models compared

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

79.3%

Better than 66% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation