Model Comparator

Compare up to four models using the same criteria.

Granite 4.0 H 1B
IBM
Exaone 4.0 1.2B (Non-reasoning)
LG AI Research

Differences only

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

Model Comparator
Metrics	Granite 4.0 H 1B IBM	Exaone 4.0 1.2B (Non-reasoning) LG AI Research	Add a model · 2/4
Intelligence	5.2	5.2
Math	6.3	Best: 24
Context window	Best: 128K	64K
Reasoning	No	No
Open weights	Yes	Yes

Intelligence

Granite 4.0 H 1B: 5.2
Exaone 4.0 1.2B (Non-reasoning): 5.2

Math

Granite 4.0 H 1B: 6.3
Exaone 4.0 1.2B (Non-reasoning): Best: 24

Context window

Granite 4.0 H 1B: Best: 128K
Exaone 4.0 1.2B (Non-reasoning): 64K

Reasoning

Granite 4.0 H 1B: No
Exaone 4.0 1.2B (Non-reasoning): No

Open weights

Granite 4.0 H 1B: Yes
Exaone 4.0 1.2B (Non-reasoning): 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.