Creator
Alibaba
Released
2025-04-28
Intelligence
7.0
Artificial Analysis Index
Coding
—
Artificial Analysis Index
In $/1M
$0.35
input tokens
Out $/1M
$1.40
output tokens
Blended $/1M
$0.61
3:1 blended
Speed
0
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
47
Humanity’s Last Exam
4
MMLU-Pro
68
SciCode
27
LiveCodeBench
28
MATH-500
87
AIME 2025
58
τ²-Bench (agentic)
32
Terminal-Bench Hard
5
IFBench
24