Creator
Alibaba
Released
2025-04-28
Intelligence
13.2
Artificial Analysis Index
Coding
9.0
Artificial Analysis Index
In $/1M
$0.11
input tokens
Out $/1M
$1.15
output tokens
Blended $/1M
$0.37
3:1 blended
Speed
61
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
59
Humanity’s Last Exam
4
MMLU-Pro
74
SciCode
23
LiveCodeBench
41
MATH-500
90
AIME 2025
19
τ²-Bench (agentic)
28
Terminal-Bench Hard
2
IFBench
33