Creator
Alibaba
Released
2026-03-02
Intelligence
22.6
Artificial Analysis Index
Coding
13.7
Artificial Analysis Index
In $/1M
$0.03
input tokens
Out $/1M
$0.15
output tokens
Blended $/1M
$0.06
3:1 blended
Speed
217
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
71
Humanity’s Last Exam
8
MMLU-Pro—
SciCode
18
LiveCodeBench—
MATH-500—
AIME 2025—
τ²-Bench (agentic)
88
Terminal-Bench Hard
11
IFBench
33