Gemini 2.5 Flash Preview (Sep '25)

Reasoning

Creator

Google DeepMind

Released

2025-09-25

Intelligence

31.1

Artificial Analysis Index

Coding

24.6

Artificial Analysis Index

In $/1M

$0.00

input tokens

Out $/1M

$0.00

output tokens

Blended $/1M

$0.00

3:1 blended

Speed

0

tokens / sec

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
79
Humanity’s Last Exam
13
MMLU-Pro
84
SciCode
41
LiveCodeBench
71
MATH-500
AIME 2025
78
τ²-Bench (agentic)
46
Terminal-Bench Hard
17
IFBench
52
Via Artificial Analysis