← All comparisons

Claude 3.5 Sonnet (Oct '24) vs DeepSeek V3 0324

Anthropic vs DeepSeek — side-by-side benchmark comparison

Claude 3.5 Sonnet (Oct '24)DeepSeek V3 0324
Intelligence Index15.922.3
Coding Index30.222.0
Math Index41.0
Output speed (tok/s)0.00.0
Blended price ($/1M)$6.56$1.21
Time to first token (s)0.00s0.00s
aime15.7%52.0%
aime 2541.0%
artificial analysis coding index30.2022.00
artificial analysis intelligence index15.9022.30
artificial analysis math index41.00
gpqa59.9%65.5%
hle3.9%5.2%
ifbench41.0%
lcr41.0%
livecodebench38.1%40.5%
math 50077.1%94.2%
mmlu pro77.2%81.9%
scicode36.6%35.8%
tau247.1%
terminalbench hard15.2%

Benchmark data from Artificial Analysis.