Granite 4.0 Micro
Creator
IBM Research
Released
2025-09-22
Intelligence
7.7
Artificial Analysis Index
Coding
5.0
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
34
Humanity’s Last Exam
5
MMLU-Pro
45
SciCode
12
LiveCodeBench
18
MATH-500—
AIME 2025
6
τ²-Bench (agentic)
13
Terminal-Bench Hard
2
IFBench
25