← All comparisons

Llama 4 Maverick vs NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)

Meta vs NVIDIA — side-by-side benchmark comparison

Llama 4 MaverickNVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
Intelligence Index18.424.3
Coding Index15.619.0
Math Index19.391.0
Output speed (tok/s)119.7122.8
Blended price ($/1M)$0.47$0.10
Time to first token (s)0.64s0.83s
aime39.0%
aime 2519.3%91.0%
artificial analysis coding index15.6019.00
artificial analysis intelligence index18.4024.30
artificial analysis math index19.3091.00
gpqa67.1%75.7%
hle4.8%10.2%
ifbench43.0%71.1%
lcr46.0%33.7%
livecodebench39.7%74.1%
math 50088.9%
mmlu pro80.9%79.4%
scicode33.1%29.6%
tau217.8%40.9%
terminalbench hard6.8%13.6%

Benchmark data from Artificial Analysis.