Creator
Alibaba
Released
2024-11-18
Intelligence
12.0
Artificial Analysis Index
Coding
—
Artificial Analysis Index
In $/1M
$0.05
input tokens
Out $/1M
$0.20
output tokens
Blended $/1M
$0.09
3:1 blended
Speed
69
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
41
Humanity’s Last Exam
4
MMLU-Pro
63
SciCode
15
LiveCodeBench
16
MATH-500
81
AIME 2025—
τ²-Bench (agentic)—
Terminal-Bench Hard—
IFBench—