← All comparisons

Claude 4.1 Opus (Non-reasoning) vs Claude 4 Opus (Reasoning)

Anthropic vs Anthropic — side-by-side benchmark comparison

Claude 4.1 Opus (Non-reasoning)Claude 4 Opus (Reasoning)
Intelligence Index36.039.0
Coding Index34.0
Math Index73.3
Output speed (tok/s)44.742.1
Blended price ($/1M)$32.81$32.81
Time to first token (s)1.63s6.80s
aime75.7%
aime 2573.3%
artificial analysis coding index34.00
artificial analysis intelligence index36.0039.00
artificial analysis math index73.30
gpqa79.6%
hle11.7%
ifbench53.7%
lcr33.7%
livecodebench63.6%
math 50098.2%
mmlu pro87.3%
scicode39.8%
tau273.4%
terminalbench hard31.1%

Benchmark data from Artificial Analysis.