← All comparisons

NVIDIA Nemotron Nano 12B v2 VL (Reasoning) vs Qwen3 30B A3B 2507 Instruct

NVIDIA vs Alibaba — side-by-side benchmark comparison

NVIDIA Nemotron Nano 12B v2 VL (Reasoning)Qwen3 30B A3B 2507 Instruct
Intelligence Index14.915.0
Coding Index11.714.2
Math Index75.066.3
Output speed (tok/s)0.0102.1
Blended price ($/1M)$0.30$0.21
Time to first token (s)0.00s0.98s
aime72.7%
aime 2575.0%66.3%
artificial analysis coding index11.7014.20
artificial analysis intelligence index14.9015.00
artificial analysis math index75.0066.30
gpqa57.2%65.9%
hle5.3%6.8%
ifbench31.9%33.1%
lcr40.0%22.7%
livecodebench69.4%51.5%
math 50097.5%
mmlu pro75.9%77.7%
scicode26.2%30.4%
tau221.3%10.2%
terminalbench hard4.5%6.1%

Benchmark data from Artificial Analysis.