Creator
Alibaba
Released
2025-10-03
Intelligence
19.7
Artificial Analysis Index
Coding
13.1
Artificial Analysis Index
In $/1M
$0.20
input tokens
Out $/1M
$0.75
output tokens
Blended $/1M
$0.34
3:1 blended
Speed
126
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
72
Humanity’s Last Exam
9
MMLU-Pro
81
SciCode
29
LiveCodeBench
70
MATH-500—
AIME 2025
82
τ²-Bench (agentic)
20
Terminal-Bench Hard
5
IFBench
45