Creator
OpenAI
Released
2025-08-07
Intelligence
41.2
Artificial Analysis Index
Coding
35.3
Artificial Analysis Index
In $/1M
$0.25
input tokens
Out $/1M
$2.00
output tokens
Blended $/1M
$0.69
3:1 blended
Speed
94
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
83
Humanity’s Last Exam
20
MMLU-Pro
84
SciCode
39
LiveCodeBench
84
MATH-500—
AIME 2025
91
τ²-Bench (agentic)
68
Terminal-Bench Hard
33
IFBench
75