← All comparisons

Hermes 4 - Llama-3.1 405B (Non-reasoning) vs Hermes 3 - Llama-3.1 70B

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

Hermes 4 - Llama-3.1 405B (Non-reasoning)Hermes 3 - Llama-3.1 70B
Intelligence Index17.610.6
Coding Index18.1
Math Index15.3
Output speed (tok/s)40.833.2
Blended price ($/1M)$1.50$0.30
Time to first token (s)0.73s0.38s
aime2.3%
aime 2515.3%
artificial analysis coding index18.10
artificial analysis intelligence index17.6010.60
artificial analysis math index15.30
gpqa53.6%40.1%
hle4.2%4.1%
ifbench34.8%
lcr20.0%
livecodebench54.6%18.8%
math 50053.8%
mmlu pro72.9%57.1%
scicode34.6%23.1%
tau226.6%
terminalbench hard9.8%

Benchmark data from Artificial Analysis.