← All comparisons

Claude 3.5 Sonnet (Oct '24) vs DeepSeek R1 0528 (May '25)

Anthropic vs DeepSeek — side-by-side benchmark comparison

Claude 3.5 Sonnet (Oct '24)DeepSeek R1 0528 (May '25)
Intelligence Index15.927.1
Coding Index30.224.0
Math Index76.0
Output speed (tok/s)0.00.0
Blended price ($/1M)$6.56$2.06
Time to first token (s)0.00s0.00s
aime15.7%89.3%
aime 2576.0%
artificial analysis coding index30.2024.00
artificial analysis intelligence index15.9027.10
artificial analysis math index76.00
gpqa59.9%81.3%
hle3.9%14.9%
ifbench39.6%
lcr54.7%
livecodebench38.1%77.0%
math 50077.1%98.3%
mmlu pro77.2%84.9%
scicode36.6%40.3%
tau236.5%
terminalbench hard15.9%

Benchmark data from Artificial Analysis.