Creator
Amazon
Released
2025-04-30
Intelligence
19.0
Artificial Analysis Index
Coding
13.8
Artificial Analysis Index
In $/1M
$2.50
input tokens
Out $/1M
$12.50
output tokens
Blended $/1M
$5.00
3:1 blended
Speed
74
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
57
Humanity’s Last Exam
5
MMLU-Pro
73
SciCode
28
LiveCodeBench
32
MATH-500
84
AIME 2025
17
τ²-Bench (agentic)
38
Terminal-Bench Hard
7
IFBench
36