← All comparisons

Claude 4.5 Sonnet (Reasoning) vs DeepSeek V3.2 Exp (Reasoning)

Anthropic vs DeepSeek — side-by-side benchmark comparison

Claude 4.5 Sonnet (Reasoning)DeepSeek V3.2 Exp (Reasoning)
Intelligence Index43.032.9
Coding Index38.633.3
Math Index88.087.7
Output speed (tok/s)55.00.0
Blended price ($/1M)$6.56$0.31
Time to first token (s)7.02s0.00s
aime
aime 2588.0%87.7%
artificial analysis coding index38.6033.30
artificial analysis intelligence index43.0032.90
artificial analysis math index88.0087.70
gpqa83.4%79.7%
hle17.3%13.8%
ifbench57.3%54.1%
lcr65.7%69.0%
livecodebench71.4%78.9%
math 500
mmlu pro87.5%85.0%
scicode44.7%37.7%
tau278.1%33.9%
terminalbench hard35.6%31.1%

Benchmark data from Artificial Analysis.