Creator
Alibaba
Released
2025-07-30
Intelligence
22.4
Artificial Analysis Index
Coding
14.6
Artificial Analysis Index
In $/1M
$0.28
input tokens
Out $/1M
$1.85
output tokens
Blended $/1M
$0.67
3:1 blended
Speed
141
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
71
Humanity’s Last Exam
10
MMLU-Pro
81
SciCode
33
LiveCodeBench
71
MATH-500
98
AIME 2025
56
τ²-Bench (agentic)
28
Terminal-Bench Hard
5
IFBench
51