← All comparisons

Claude 3.5 Sonnet (Oct '24) vs DeepSeek V3.1 (Reasoning)

Anthropic vs DeepSeek — side-by-side benchmark comparison

Claude 3.5 Sonnet (Oct '24)DeepSeek V3.1 (Reasoning)
Intelligence Index15.927.7
Coding Index30.229.7
Math Index89.7
Output speed (tok/s)0.00.0
Blended price ($/1M)$6.56$0.86
Time to first token (s)0.00s0.00s
aime15.7%
aime 2589.7%
artificial analysis coding index30.2029.70
artificial analysis intelligence index15.9027.70
artificial analysis math index89.70
gpqa59.9%77.9%
hle3.9%13.0%
ifbench41.5%
lcr53.3%
livecodebench38.1%78.4%
math 50077.1%
mmlu pro77.2%85.1%
scicode36.6%39.1%
tau237.4%
terminalbench hard25.0%

Benchmark data from Artificial Analysis.