← All comparisons

Claude 4.1 Opus (Reasoning) vs DeepSeek V3.2 Speciale

Anthropic vs DeepSeek — side-by-side benchmark comparison

Claude 4.1 Opus (Reasoning)DeepSeek V3.2 Speciale
Intelligence Index42.029.4
Coding Index36.537.9
Math Index80.396.7
Output speed (tok/s)44.50.0
Blended price ($/1M)$32.81$0.00
Time to first token (s)8.55s0.00s
aime
aime 2580.3%96.7%
artificial analysis coding index36.5037.90
artificial analysis intelligence index42.0029.40
artificial analysis math index80.3096.70
gpqa80.9%87.1%
hle11.9%26.1%
ifbench55.4%63.9%
lcr66.3%59.3%
livecodebench65.4%89.6%
math 500
mmlu pro88.0%86.3%
scicode40.9%44.0%
tau271.4%0.0%
terminalbench hard34.3%34.8%

Benchmark data from Artificial Analysis.