← All comparisons

Hermes 4 - Llama-3.1 405B (Reasoning) vs Qwen3 VL 30B A3B Instruct

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

Hermes 4 - Llama-3.1 405B (Reasoning)Qwen3 VL 30B A3B Instruct
Intelligence Index18.616.0
Coding Index16.014.3
Math Index69.772.3
Output speed (tok/s)38.6123.5
Blended price ($/1M)$1.50$0.30
Time to first token (s)0.79s1.07s
aime
aime 2569.7%72.3%
artificial analysis coding index16.0014.30
artificial analysis intelligence index18.6016.00
artificial analysis math index69.7072.30
gpqa72.7%69.5%
hle10.3%6.4%
ifbench32.7%33.1%
lcr20.7%23.7%
livecodebench68.6%47.6%
math 500
mmlu pro82.9%76.4%
scicode25.2%30.8%
tau222.2%19.0%
terminalbench hard11.4%6.1%

Benchmark data from Artificial Analysis.