← All comparisons

NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) vs DeepSeek R1 Distill Qwen 32B

NVIDIA vs DeepSeek — side-by-side benchmark comparison

NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)DeepSeek R1 Distill Qwen 32B
Intelligence Index10.117.2
Coding Index5.9
Math Index26.763.0
Output speed (tok/s)227.40.0
Blended price ($/1M)$0.30$0.00
Time to first token (s)0.63s0.00s
aime68.7%
aime 2526.7%63.0%
artificial analysis coding index5.90
artificial analysis intelligence index10.1017.20
artificial analysis math index26.7063.00
gpqa43.9%61.5%
hle4.5%5.5%
ifbench25.9%22.9%
lcr17.0%9.7%
livecodebench34.5%27.0%
math 50094.1%
mmlu pro64.9%73.9%
scicode17.6%37.6%
tau219.3%
terminalbench hard0.0%

Benchmark data from Artificial Analysis.