Creator
Alibaba
Released
2025-11-03
Intelligence
32.5
Artificial Analysis Index
Coding
24.5
Artificial Analysis Index
In $/1M
$1.20
input tokens
Out $/1M
$6.00
output tokens
Blended $/1M
$2.40
3:1 blended
Speed
45
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
78
Humanity’s Last Exam
12
MMLU-Pro
82
SciCode
39
LiveCodeBench
54
MATH-500—
AIME 2025
82
τ²-Bench (agentic)
84
Terminal-Bench Hard
17
IFBench
54