Creator
Alibaba
Released
2026-02-16
Intelligence
40.1
Artificial Analysis Index
Coding
37.4
Artificial Analysis Index
In $/1M
$0.60
input tokens
Out $/1M
$3.60
output tokens
Blended $/1M
$1.35
3:1 blended
Speed
53
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
86
Humanity’s Last Exam
19
MMLU-Pro—
SciCode
41
LiveCodeBench—
MATH-500—
AIME 2025—
τ²-Bench (agentic)
84
Terminal-Bench Hard
36
IFBench
52