← All comparisons

NVIDIA Nemotron Nano 12B v2 VL (Reasoning) vs Hermes 4 - Llama-3.1 405B (Reasoning)

NVIDIA vs Nous Research — side-by-side benchmark comparison

NVIDIA Nemotron Nano 12B v2 VL (Reasoning)Hermes 4 - Llama-3.1 405B (Reasoning)
Intelligence Index14.918.6
Coding Index11.716.0
Math Index75.069.7
Output speed (tok/s)0.038.6
Blended price ($/1M)$0.30$1.50
Time to first token (s)0.00s0.79s
aime
aime 2575.0%69.7%
artificial analysis coding index11.7016.00
artificial analysis intelligence index14.9018.60
artificial analysis math index75.0069.70
gpqa57.2%72.7%
hle5.3%10.3%
ifbench31.9%32.7%
lcr40.0%20.7%
livecodebench69.4%68.6%
math 500
mmlu pro75.9%82.9%
scicode26.2%25.2%
tau221.3%22.2%
terminalbench hard4.5%11.4%

Benchmark data from Artificial Analysis.