← All comparisons

Hermes 4 - Llama-3.1 405B (Reasoning) vs GPT-5 mini (minimal)

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

Hermes 4 - Llama-3.1 405B (Reasoning)GPT-5 mini (minimal)
Intelligence Index18.620.7
Coding Index16.021.9
Math Index69.746.7
Output speed (tok/s)38.689.3
Blended price ($/1M)$1.50$0.69
Time to first token (s)0.79s0.73s
aime
aime 2569.7%46.7%
artificial analysis coding index16.0021.90
artificial analysis intelligence index18.6020.70
artificial analysis math index69.7046.70
gpqa72.7%68.7%
hle10.3%5.0%
ifbench32.7%45.6%
lcr20.7%35.7%
livecodebench68.6%54.5%
math 500
mmlu pro82.9%77.5%
scicode25.2%36.9%
tau222.2%31.9%
terminalbench hard11.4%14.4%

Benchmark data from Artificial Analysis.