Creator
Anthropic
Released
2025-05-22
Intelligence
38.7
Artificial Analysis Index
Coding
34.1
Artificial Analysis Index
In $/1M
$3.75
input tokens
Out $/1M
$15.00
output tokens
Blended $/1M
$6.56
3:1 blended
Speed
60
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
78
Humanity’s Last Exam
10
MMLU-Pro
84
SciCode
40
LiveCodeBench
66
MATH-500
99
AIME 2025
74
τ²-Bench (agentic)
65
Terminal-Bench Hard
31
IFBench
55