← All comparisons

Hermes 4 - Llama-3.1 70B (Non-reasoning) vs DeepSeek R1 Distill Llama 8B

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

Hermes 4 - Llama-3.1 70B (Non-reasoning)DeepSeek R1 Distill Llama 8B
Intelligence Index12.612.1
Coding Index9.2
Math Index11.341.3
Output speed (tok/s)94.30.0
Blended price ($/1M)$0.20$0.00
Time to first token (s)0.61s0.00s
aime33.3%
aime 2511.3%41.3%
artificial analysis coding index9.20
artificial analysis intelligence index12.6012.10
artificial analysis math index11.3041.30
gpqa49.1%30.2%
hle3.6%4.2%
ifbench29.0%17.6%
lcr2.0%0.0%
livecodebench26.9%23.3%
math 50085.3%
mmlu pro66.4%54.3%
scicode27.7%11.9%
tau221.6%
terminalbench hard0.0%

Benchmark data from Artificial Analysis.