Creator
Alibaba
Released
2025-04-28
Intelligence
10.6
Artificial Analysis Index
Coding
7.1
Artificial Analysis Index
In $/1M
$0.18
input tokens
Out $/1M
$0.20
output tokens
Blended $/1M
$0.18
3:1 blended
Speed
63
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
45
Humanity’s Last Exam
3
MMLU-Pro
64
SciCode
17
LiveCodeBench
20
MATH-500
83
AIME 2025
24
τ²-Bench (agentic)
25
Terminal-Bench Hard
2
IFBench
29