← All comparisons

DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) vs EXAONE 4.0 32B (Reasoning)

Nous Research vs LG AI Research — side-by-side benchmark comparison

DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)EXAONE 4.0 32B (Reasoning)
Intelligence Index7.616.7
Coding Index14.0
Math Index80.0
Output speed (tok/s)0.00.0
Blended price ($/1M)$0.00$0.00
Time to first token (s)0.00s0.00s
aime0.0%84.3%
aime 2580.0%
artificial analysis coding index14.00
artificial analysis intelligence index7.6016.70
artificial analysis math index80.00
gpqa27.0%73.9%
hle4.3%10.5%
ifbench36.3%
lcr14.0%
livecodebench8.5%74.7%
math 50021.8%97.7%
mmlu pro36.5%81.8%
scicode9.1%34.4%
tau217.3%
terminalbench hard3.8%

Benchmark data from Artificial Analysis.