Gemma 4 26B A4B
Reasoning
Creator
Google DeepMind
Released
2026-04-02
Intelligence
31.2
Artificial Analysis Index
Coding
22.4
Artificial Analysis Index
In $/1M
$0.13
input tokens
Out $/1M
$0.40
output tokens
Blended $/1M
$0.20
3:1 blended
Speed
0
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
79
Humanity’s Last Exam
18
MMLU-Pro—
SciCode
40
LiveCodeBench—
MATH-500—
AIME 2025—
τ²-Bench (agentic)
44
Terminal-Bench Hard
14
IFBench
72