Creator
Alibaba
Released
2026-02-24
Intelligence
35.9
Artificial Analysis Index
Coding
31.6
Artificial Analysis Index
In $/1M
$0.40
input tokens
Out $/1M
$3.20
output tokens
Blended $/1M
$1.10
3:1 blended
Speed
166
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
83
Humanity’s Last Exam
15
MMLU-Pro—
SciCode
36
LiveCodeBench—
MATH-500—
AIME 2025—
τ²-Bench (agentic)
85
Terminal-Bench Hard
30
IFBench
51