Creator
Amazon
Released
2025-10-29
Intelligence
24.6
Artificial Analysis Index
Coding
13.6
Artificial Analysis Index
In $/1M
$0.30
input tokens
Out $/1M
$2.50
output tokens
Blended $/1M
$0.85
3:1 blended
Speed
175
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
70
Humanity’s Last Exam
4
MMLU-Pro
79
SciCode
33
LiveCodeBench
47
MATH-500—
AIME 2025
47
τ²-Bench (agentic)
72
Terminal-Bench Hard
4
IFBench
61