← All comparisons

Claude Sonnet 4.6 (Non-reasoning, Low Effort) vs DeepSeek V4 Pro (Non-reasoning)

Anthropic vs DeepSeek — side-by-side benchmark comparison

Claude Sonnet 4.6 (Non-reasoning, Low Effort)DeepSeek V4 Pro (Non-reasoning)
Intelligence Index42.639.3
Coding Index43.038.4
Math Index
Output speed (tok/s)54.953.3
Blended price ($/1M)$6.56$0.54
Time to first token (s)1.13s1.18s
aime
aime 25
artificial analysis coding index43.0038.40
artificial analysis intelligence index42.6039.30
artificial analysis math index
gpqa79.7%71.7%
hle10.8%7.7%
ifbench42.4%45.8%
lcr58.7%45.0%
livecodebench
math 500
mmlu pro
scicode44.1%42.4%
tau278.9%91.2%
terminalbench hard42.4%36.4%

Benchmark data from Artificial Analysis.