← All comparisons

Hermes 4 - Llama-3.1 70B (Non-reasoning) vs GPT-5 mini (minimal)

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

Hermes 4 - Llama-3.1 70B (Non-reasoning)GPT-5 mini (minimal)
Intelligence Index12.620.7
Coding Index9.221.9
Math Index11.346.7
Output speed (tok/s)94.389.3
Blended price ($/1M)$0.20$0.69
Time to first token (s)0.61s0.73s
aime
aime 2511.3%46.7%
artificial analysis coding index9.2021.90
artificial analysis intelligence index12.6020.70
artificial analysis math index11.3046.70
gpqa49.1%68.7%
hle3.6%5.0%
ifbench29.0%45.6%
lcr2.0%35.7%
livecodebench26.9%54.5%
math 500
mmlu pro66.4%77.5%
scicode27.7%36.9%
tau221.6%31.9%
terminalbench hard0.0%14.4%

Benchmark data from Artificial Analysis.