Gemini 2.5 Flash-Lite Preview (Sep '25)
Reasoning
Creator
Google DeepMind
Released
2025-09-08
Intelligence
21.6
Artificial Analysis Index
Coding
18.2
Artificial Analysis Index
In $/1M
$0.10
input tokens
Out $/1M
$0.40
output tokens
Blended $/1M
$0.17
3:1 blended
Speed
0
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
71
Humanity’s Last Exam
7
MMLU-Pro
81
SciCode
29
LiveCodeBench
69
MATH-500—
AIME 2025
69
τ²-Bench (agentic)
31
Terminal-Bench Hard
13
IFBench
53