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
Via Artificial Analysis