Creator
Alibaba
Released
2025-01-28
Intelligence
16.3
Artificial Analysis Index
Coding
—
Artificial Analysis Index
In $/1M
$1.60
input tokens
Out $/1M
$6.40
output tokens
Blended $/1M
$2.80
3:1 blended
Speed
0
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
59
Humanity’s Last Exam
5
MMLU-Pro
76
SciCode
34
LiveCodeBench
36
MATH-500
83
AIME 2025—
τ²-Bench (agentic)—
Terminal-Bench Hard—
IFBench—