← All comparisons

Claude 4.5 Sonnet (Reasoning) vs Claude 4 Sonnet (Non-reasoning)

Anthropic vs Anthropic — side-by-side benchmark comparison

Claude 4.5 Sonnet (Reasoning)Claude 4 Sonnet (Non-reasoning)
Intelligence Index43.033.0
Coding Index38.630.6
Math Index88.038.0
Output speed (tok/s)55.053.9
Blended price ($/1M)$6.56$6.56
Time to first token (s)7.02s0.82s
aime40.7%
aime 2588.0%38.0%
artificial analysis coding index38.6030.60
artificial analysis intelligence index43.0033.00
artificial analysis math index88.0038.00
gpqa83.4%68.3%
hle17.3%4.0%
ifbench57.3%45.4%
lcr65.7%44.3%
livecodebench71.4%44.9%
math 50093.4%
mmlu pro87.5%83.7%
scicode44.7%37.3%
tau278.1%52.3%
terminalbench hard35.6%27.3%

Benchmark data from Artificial Analysis.