← All comparisons

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

Anthropic vs Anthropic — side-by-side benchmark comparison

Claude 4 Sonnet (Non-reasoning)Claude 4.1 Opus (Reasoning)
Intelligence Index33.042.0
Coding Index30.636.5
Math Index38.080.3
Output speed (tok/s)53.944.5
Blended price ($/1M)$6.56$32.81
Time to first token (s)0.82s8.55s
aime40.7%
aime 2538.0%80.3%
artificial analysis coding index30.6036.50
artificial analysis intelligence index33.0042.00
artificial analysis math index38.0080.30
gpqa68.3%80.9%
hle4.0%11.9%
ifbench45.4%55.4%
lcr44.3%66.3%
livecodebench44.9%65.4%
math 50093.4%
mmlu pro83.7%88.0%
scicode37.3%40.9%
tau252.3%71.4%
terminalbench hard27.3%34.3%

Benchmark data from Artificial Analysis.