Creator
Alibaba
Released
2025-04-28
Intelligence
5.7
Artificial Analysis Index
Coding
1.4
Artificial Analysis Index
In $/1M
$0.11
input tokens
Out $/1M
$0.42
output tokens
Blended $/1M
$0.19
3:1 blended
Speed
0
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
23
Humanity’s Last Exam
5
MMLU-Pro
23
SciCode
4
LiveCodeBench
7
MATH-500
52
AIME 2025
10
τ²-Bench (agentic)
15
Terminal-Bench Hard
0
IFBench
22