← All comparisons

Claude 3.5 Sonnet (Oct '24) vs DeepSeek V3 (Dec '24)

Anthropic vs DeepSeek — side-by-side benchmark comparison

Claude 3.5 Sonnet (Oct '24)DeepSeek V3 (Dec '24)
Intelligence Index15.916.5
Coding Index30.216.4
Math Index26.0
Output speed (tok/s)0.00.0
Blended price ($/1M)$6.56$0.52
Time to first token (s)0.00s0.00s
aime15.7%25.3%
aime 2526.0%
artificial analysis coding index30.2016.40
artificial analysis intelligence index15.9016.50
artificial analysis math index26.00
gpqa59.9%55.7%
hle3.9%3.6%
ifbench34.8%
lcr29.0%
livecodebench38.1%35.9%
math 50077.1%88.7%
mmlu pro77.2%75.2%
scicode36.6%35.4%
tau222.8%
terminalbench hard6.8%

Benchmark data from Artificial Analysis.