← All comparisons

Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) vs Qwen3 30B A3B 2507 (Reasoning)

NVIDIA vs Alibaba — side-by-side benchmark comparison

Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)Qwen3 30B A3B 2507 (Reasoning)
Intelligence Index14.422.4
Coding Index14.6
Math Index50.056.3
Output speed (tok/s)0.0155.3
Blended price ($/1M)$0.00$0.67
Time to first token (s)0.00s1.02s
aime70.7%90.7%
aime 2550.0%56.3%
artificial analysis coding index14.60
artificial analysis intelligence index14.4022.40
artificial analysis math index50.0056.30
gpqa40.8%70.7%
hle5.1%9.8%
ifbench25.5%50.7%
lcr0.0%59.0%
livecodebench49.3%70.7%
math 50094.7%97.6%
mmlu pro55.6%80.5%
scicode10.1%33.3%
tau211.7%28.1%
terminalbench hard5.3%

Benchmark data from Artificial Analysis.