← All comparisons

Hermes 4 - Llama-3.1 70B (Non-reasoning) vs Llama 3.2 Instruct 3B

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

Hermes 4 - Llama-3.1 70B (Non-reasoning)Llama 3.2 Instruct 3B
Intelligence Index12.69.7
Coding Index9.2
Math Index11.33.3
Output speed (tok/s)94.352.7
Blended price ($/1M)$0.20$0.15
Time to first token (s)0.61s0.65s
aime6.7%
aime 2511.3%3.3%
artificial analysis coding index9.20
artificial analysis intelligence index12.609.70
artificial analysis math index11.303.30
gpqa49.1%25.5%
hle3.6%5.2%
ifbench29.0%26.2%
lcr2.0%2.0%
livecodebench26.9%8.3%
math 50048.9%
mmlu pro66.4%34.7%
scicode27.7%5.2%
tau221.6%21.1%
terminalbench hard0.0%

Benchmark data from Artificial Analysis.