Creator
Alibaba
Released
2025-04-28
Intelligence
16.2
Artificial Analysis Index
Coding
13.1
Artificial Analysis Index
In $/1M
$0.23
input tokens
Out $/1M
$2.22
output tokens
Blended $/1M
$0.73
3:1 blended
Speed
65
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
60
Humanity’s Last Exam
4
MMLU-Pro
77
SciCode
32
LiveCodeBench
52
MATH-500
96
AIME 2025
56
τ²-Bench (agentic)
35
Terminal-Bench Hard
4
IFBench
41