← All comparisons

Gemini 3.1 Pro Preview vs Hermes 4 - Llama-3.1 405B (Non-reasoning)

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

Gemini 3.1 Pro PreviewHermes 4 - Llama-3.1 405B (Non-reasoning)
Intelligence Index57.217.6
Coding Index55.518.1
Math Index15.3
Output speed (tok/s)136.840.8
Blended price ($/1M)$4.50$1.50
Time to first token (s)25.68s0.73s
aime
aime 2515.3%
artificial analysis coding index55.5018.10
artificial analysis intelligence index57.2017.60
artificial analysis math index15.30
gpqa94.1%53.6%
hle44.7%4.2%
ifbench77.1%34.8%
lcr72.7%20.0%
livecodebench54.6%
math 500
mmlu pro72.9%
scicode58.9%34.6%
tau295.6%26.6%
terminalbench hard53.8%9.8%

Benchmark data from Artificial Analysis.