Model Comparator

Compare up to four models using the same criteria.

K-EXAONE (Reasoning)
LG AI Research
DeepSeek V3.2 Speciale
DeepSeek

Differences only

✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.

Model Comparator
Metrics	K-EXAONE (Reasoning) LG AI Research	DeepSeek V3.2 Speciale DeepSeek	Add a model · 2/4
Intelligence	14.4	Best: 14.5
Coding	32.1	—
Math	90.3	Best: 96.7
Context window	Best: 2.02M	128K
Reasoning	Yes	Yes
Open weights	Yes	Yes

Intelligence

K-EXAONE (Reasoning): 14.4
DeepSeek V3.2 Speciale: Best: 14.5

Coding

K-EXAONE (Reasoning): 32.1
DeepSeek V3.2 Speciale: —

Math

K-EXAONE (Reasoning): 90.3
DeepSeek V3.2 Speciale: Best: 96.7

Context window

K-EXAONE (Reasoning): Best: 2.02M
DeepSeek V3.2 Speciale: 128K

Reasoning

K-EXAONE (Reasoning): Yes
DeepSeek V3.2 Speciale: Yes

Open weights

K-EXAONE (Reasoning): Yes
DeepSeek V3.2 Speciale: Yes

Each reasoning level remains a separate configuration.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.