← All benchmarks

Claude 4.1 Opus (Reasoning)

Anthropic · Released 2025-08-05 · Independent benchmark scores from Artificial Analysis

Intelligence Index
33.7
Output speed
0.0
tokens/sec
Blended price
$30.00
per 1M tokens
Time to first token
0.00s

Model metadata

Model IDccbfa8c3-a762-480b-aade-34fb9697f98c
Slugclaude-4-1-opus-thinking
Release date2025-08-05
ProviderAnthropic
Provider sluganthropic
Output speed0.0 tok/s
Time to first token0.00s
Time to first answer0.00s
Blended price ($/1M)$30.00
Input price ($/1M)$15.00
Output price ($/1M)$75.00

All evaluation scores (17)

aime
aime 2580.3%
artificial analysis coding index
artificial analysis intelligence index33.70
artificial analysis math index80.30
gpqa80.9%
hle11.9%
ifbench55.4%
lcr66.3%
livecodebench65.4%
math 500
mmlu pro88.0%
scicode40.9%
tau banking
tau271.4%
terminalbench hard34.3%
terminalbench v2 1

Source: artificialanalysis.ai/models/claude-4-1-opus-thinking

Benchmark data from Artificial Analysis.