Gemma 4 31B
Reasoning
Creator
Google DeepMind
Released
2026-04-02
Intelligence
39.2
Artificial Analysis Index
Coding
38.7
Artificial Analysis Index
In $/1M
$0.00
input tokens
Out $/1M
$0.00
output tokens
Blended $/1M
$0.00
3:1 blended
Speed
35
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
86
Humanity’s Last Exam
23
MMLU-Pro—
SciCode
43
LiveCodeBench—
MATH-500—
AIME 2025—
τ²-Bench (agentic)
60
Terminal-Bench Hard
36
IFBench
76