Creator
Amazon
Released
2024-12-03
Intelligence
12.7
Artificial Analysis Index
Coding
5.1
Artificial Analysis Index
In $/1M
$0.06
input tokens
Out $/1M
$0.24
output tokens
Blended $/1M
$0.10
3:1 blended
Speed
168
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
43
Humanity’s Last Exam
5
MMLU-Pro
59
SciCode
14
LiveCodeBench
17
MATH-500
76
AIME 2025
7
τ²-Bench (agentic)
18
Terminal-Bench Hard
1
IFBench
34