← All comparisons

Hermes 4 - Llama-3.1 70B (Non-reasoning) vs DeepSeek R1 Distill Qwen 1.5B

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

Hermes 4 - Llama-3.1 70B (Non-reasoning)DeepSeek R1 Distill Qwen 1.5B
Intelligence Index12.69.1
Coding Index9.2
Math Index11.322.0
Output speed (tok/s)94.30.0
Blended price ($/1M)$0.20$0.00
Time to first token (s)0.61s0.00s
aime17.7%
aime 2511.3%22.0%
artificial analysis coding index9.20
artificial analysis intelligence index12.609.10
artificial analysis math index11.3022.00
gpqa49.1%9.8%
hle3.6%3.3%
ifbench29.0%13.2%
lcr2.0%0.3%
livecodebench26.9%7.0%
math 50068.7%
mmlu pro66.4%26.9%
scicode27.7%6.6%
tau221.6%
terminalbench hard0.0%

Benchmark data from Artificial Analysis.