Model Comparator

Compare up to four models using the same criteria.

Granite 4.0 1B
IBM
Command-R (Mar '24)
Cohere

Differences only

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

Model Comparator
Metrics	Granite 4.0 1B IBM	Command-R (Mar '24) Cohere	Add a model · 2/4
Intelligence	5	5
Math	6.3	—
Context window	128K	128K
Reasoning	No	No
Open weights	Yes	Yes

Intelligence

Granite 4.0 1B: 5
Command-R (Mar '24): 5

Math

Granite 4.0 1B: 6.3
Command-R (Mar '24): —

Context window

Granite 4.0 1B: 128K
Command-R (Mar '24): 128K

Reasoning

Granite 4.0 1B: No
Command-R (Mar '24): No

Open weights

Granite 4.0 1B: Yes
Command-R (Mar '24): 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.