← All comparisons

Claude 4.5 Sonnet (Reasoning) vs DeepSeek R1 (Jan '25)

Anthropic vs DeepSeek — side-by-side benchmark comparison

Claude 4.5 Sonnet (Reasoning)DeepSeek R1 (Jan '25)
Intelligence Index43.018.8
Coding Index38.615.9
Math Index88.068.0
Output speed (tok/s)55.00.0
Blended price ($/1M)$6.56$2.43
Time to first token (s)7.02s0.00s
aime68.3%
aime 2588.0%68.0%
artificial analysis coding index38.6015.90
artificial analysis intelligence index43.0018.80
artificial analysis math index88.0068.00
gpqa83.4%70.8%
hle17.3%9.3%
ifbench57.3%39.0%
lcr65.7%52.3%
livecodebench71.4%61.7%
math 50096.6%
mmlu pro87.5%84.4%
scicode44.7%35.7%
tau278.1%11.4%
terminalbench hard35.6%6.1%

Benchmark data from Artificial Analysis.