Claude Opus 4.5

Reasoning

Creator

Anthropic

Released

2025-11-24

Intelligence

49.7

Artificial Analysis Index

Coding

47.8

Artificial Analysis Index

In $/1M

$6.25

input tokens

Out $/1M

$25.00

output tokens

Blended $/1M

$10.94

3:1 blended

Speed

79

tokens / sec

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
87
Humanity’s Last Exam
28
MMLU-Pro
90
SciCode
50
LiveCodeBench
87
MATH-500
AIME 2025
91
τ²-Bench (agentic)
89
Terminal-Bench Hard
47
IFBench
58
Via Artificial Analysis