← All comparisons

Hermes 4 - Llama-3.1 70B (Reasoning) vs Hermes 3 - Llama-3.1 70B

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

Hermes 4 - Llama-3.1 70B (Reasoning)Hermes 3 - Llama-3.1 70B
Intelligence Index16.010.6
Coding Index14.4
Math Index68.7
Output speed (tok/s)92.833.2
Blended price ($/1M)$0.20$0.30
Time to first token (s)0.64s0.38s
aime2.3%
aime 2568.7%
artificial analysis coding index14.40
artificial analysis intelligence index16.0010.60
artificial analysis math index68.70
gpqa69.9%40.1%
hle7.9%4.1%
ifbench31.3%
lcr6.7%
livecodebench65.3%18.8%
math 50053.8%
mmlu pro81.1%57.1%
scicode34.1%23.1%
tau222.5%
terminalbench hard4.5%

Benchmark data from Artificial Analysis.