Creator
Amazon
Released
2025-10-29
Intelligence
11.8
Artificial Analysis Index
Coding
—
Artificial Analysis Index
In $/1M
$0.30
input tokens
Out $/1M
$2.50
output tokens
Blended $/1M
$0.85
3:1 blended
Speed
215
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
60
Humanity’s Last Exam
3
MMLU-Pro
74
SciCode
24
LiveCodeBench
35
MATH-500—
AIME 2025
34
τ²-Bench (agentic)
62
Terminal-Bench Hard
7
IFBench
41