Creator
Alibaba
Released
2025-04-28
Intelligence
14.5
Artificial Analysis Index
Coding
—
Artificial Analysis Index
In $/1M
$0.15
input tokens
Out $/1M
$0.59
output tokens
Blended $/1M
$0.26
3:1 blended
Speed
95
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
54
Humanity’s Last Exam
4
MMLU-Pro
73
SciCode
28
LiveCodeBench
29
MATH-500
87
AIME 2025
20
τ²-Bench (agentic)—
Terminal-Bench Hard—
IFBench
31