← All comparisons

Exaone 4.0 1.2B (Reasoning) vs Hermes 3 - Llama-3.1 70B

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

Exaone 4.0 1.2B (Reasoning)Hermes 3 - Llama-3.1 70B
Intelligence Index8.310.6
Coding Index3.1
Math Index50.3
Output speed (tok/s)0.033.2
Blended price ($/1M)$0.00$0.30
Time to first token (s)0.00s0.38s
aime2.3%
aime 2550.3%
artificial analysis coding index3.10
artificial analysis intelligence index8.3010.60
artificial analysis math index50.30
gpqa51.5%40.1%
hle5.8%4.1%
ifbench23.0%
lcr0.0%
livecodebench51.6%18.8%
math 50053.8%
mmlu pro58.8%57.1%
scicode9.3%23.1%
tau216.4%
terminalbench hard0.0%

Benchmark data from Artificial Analysis.