Creator
Anthropic
Released
2025-10-15
Intelligence
31.0
Artificial Analysis Index
Coding
29.6
Artificial Analysis Index
In $/1M
$1.25
input tokens
Out $/1M
$5.00
output tokens
Blended $/1M
$2.19
3:1 blended
Speed
136
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
65
Humanity’s Last Exam
4
MMLU-Pro
80
SciCode
34
LiveCodeBench
51
MATH-500—
AIME 2025
39
τ²-Bench (agentic)
32
Terminal-Bench Hard
27
IFBench
42