← All comparisons

Hermes 4 - Llama-3.1 405B (Reasoning) vs DeepSeek R1 Distill Qwen 32B

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

Hermes 4 - Llama-3.1 405B (Reasoning)DeepSeek R1 Distill Qwen 32B
Intelligence Index18.617.2
Coding Index16.0
Math Index69.763.0
Output speed (tok/s)38.60.0
Blended price ($/1M)$1.50$0.00
Time to first token (s)0.79s0.00s
aime68.7%
aime 2569.7%63.0%
artificial analysis coding index16.00
artificial analysis intelligence index18.6017.20
artificial analysis math index69.7063.00
gpqa72.7%61.5%
hle10.3%5.5%
ifbench32.7%22.9%
lcr20.7%9.7%
livecodebench68.6%27.0%
math 50094.1%
mmlu pro82.9%73.9%
scicode25.2%37.6%
tau222.2%
terminalbench hard11.4%

Benchmark data from Artificial Analysis.