Claude Opus 4.6

Adaptive Reasoning, Max Effort

Creator

Anthropic

Released

2026-02-05

Intelligence

52.9

Artificial Analysis Index

Coding

48.1

Artificial Analysis Index

In $/1M

$6.25

input tokens

Out $/1M

$25.00

output tokens

Blended $/1M

$10.94

3:1 blended

Speed

65

tokens / sec

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
90
Humanity’s Last Exam
37
MMLU-Pro
SciCode
52
LiveCodeBench
MATH-500
AIME 2025
τ²-Bench (agentic)
92
Terminal-Bench Hard
46
IFBench
53
Via Artificial Analysis