← All comparisons

Gemini 3.1 Flash-Lite vs Hermes 4 - Llama-3.1 405B (Reasoning)

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

Gemini 3.1 Flash-LiteHermes 4 - Llama-3.1 405B (Reasoning)
Intelligence Index33.518.6
Coding Index30.116.0
Math Index69.7
Output speed (tok/s)304.938.6
Blended price ($/1M)$0.56$1.50
Time to first token (s)5.00s0.79s
aime
aime 2569.7%
artificial analysis coding index30.1016.00
artificial analysis intelligence index33.5018.60
artificial analysis math index69.70
gpqa82.2%72.7%
hle16.2%10.3%
ifbench77.2%32.7%
lcr65.3%20.7%
livecodebench68.6%
math 500
mmlu pro82.9%
scicode41.9%25.2%
tau231.3%22.2%
terminalbench hard24.2%11.4%

Benchmark data from Artificial Analysis.