← All comparisons

DeepSeek V3.2 Exp (Reasoning) vs Qwen3 235B A22B (Reasoning)

DeepSeek vs Alibaba — side-by-side benchmark comparison

DeepSeek V3.2 Exp (Reasoning)Qwen3 235B A22B (Reasoning)
Intelligence Index32.919.8
Coding Index33.317.4
Math Index87.782.0
Output speed (tok/s)0.058.3
Blended price ($/1M)$0.31$2.63
Time to first token (s)0.00s1.37s
aime84.0%
aime 2587.7%82.0%
artificial analysis coding index33.3017.40
artificial analysis intelligence index32.9019.80
artificial analysis math index87.7082.00
gpqa79.7%70.0%
hle13.8%11.7%
ifbench54.1%38.7%
lcr69.0%0.0%
livecodebench78.9%62.2%
math 50093.0%
mmlu pro85.0%82.8%
scicode37.7%39.9%
tau233.9%24.0%
terminalbench hard31.1%6.1%

Benchmark data from Artificial Analysis.