Claude Opus 4.7

Adaptive Reasoning, Max Effort

Creator

Anthropic

Released

2026-04-16

Intelligence

57.3

Artificial Analysis Index

Coding

52.5

Artificial Analysis Index

In $/1M

$6.25

input tokens

Out $/1M

$25.00

output tokens

Blended $/1M

$10.94

3:1 blended

Speed

62

tokens / sec

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
91
Humanity’s Last Exam
40
MMLU-Pro
SciCode
55
LiveCodeBench
MATH-500
AIME 2025
τ²-Bench (agentic)
89
Terminal-Bench Hard
52
IFBench
59
Via Artificial Analysis