← All comparisons

Molmo2-8B vs Hermes 4 - Llama-3.1 405B (Non-reasoning)

Allen Institute for AI vs Nous Research — side-by-side benchmark comparison

Molmo2-8BHermes 4 - Llama-3.1 405B (Non-reasoning)
Intelligence Index7.317.6
Coding Index4.418.1
Math Index15.3
Output speed (tok/s)0.040.8
Blended price ($/1M)$0.00$1.50
Time to first token (s)0.00s0.73s
aime
aime 2515.3%
artificial analysis coding index4.4018.10
artificial analysis intelligence index7.3017.60
artificial analysis math index15.30
gpqa42.5%53.6%
hle4.4%4.2%
ifbench26.9%34.8%
lcr0.0%20.0%
livecodebench54.6%
math 500
mmlu pro72.9%
scicode13.3%34.6%
tau20.0%26.6%
terminalbench hard0.0%9.8%

Benchmark data from Artificial Analysis.