← All comparisons

Hermes 4 - Llama-3.1 70B (Reasoning) vs DeepSeek R1 Distill Qwen 14B

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

Hermes 4 - Llama-3.1 70B (Reasoning)DeepSeek R1 Distill Qwen 14B
Intelligence Index16.015.8
Coding Index14.4
Math Index68.755.7
Output speed (tok/s)92.80.0
Blended price ($/1M)$0.20$0.00
Time to first token (s)0.64s0.00s
aime66.7%
aime 2568.7%55.7%
artificial analysis coding index14.40
artificial analysis intelligence index16.0015.80
artificial analysis math index68.7055.70
gpqa69.9%48.4%
hle7.9%4.4%
ifbench31.3%22.1%
lcr6.7%7.0%
livecodebench65.3%37.6%
math 50094.9%
mmlu pro81.1%74.0%
scicode34.1%23.9%
tau222.5%
terminalbench hard4.5%

Benchmark data from Artificial Analysis.