Gemini 2.5 Flash Preview
Reasoning
Creator
Google DeepMind
Released
2025-04-17
Intelligence
24.3
Artificial Analysis Index
Coding
—
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
70
Humanity’s Last Exam
12
MMLU-Pro
80
SciCode
36
LiveCodeBench
51
MATH-500
98
AIME 2025—
τ²-Bench (agentic)—
Terminal-Bench Hard—
IFBench—