Model Comparator

Compare up to four models using the same criteria.

Devstral Small (Jul '25)
Mistral
Mistral Large 2 (Nov '24)
Mistral

Differences only

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

Model Comparator
Metrics	Devstral Small (Jul '25) Mistral	Mistral Large 2 (Nov '24) Mistral	Add a model · 2/4
Intelligence	7.6	7.6
Math	Best: 29.3	14
Context window	Best: 256K	128K
Reasoning	No	No
Open weights	Yes	Yes

Intelligence

Devstral Small (Jul '25): 7.6
Mistral Large 2 (Nov '24): 7.6

Math

Devstral Small (Jul '25): Best: 29.3
Mistral Large 2 (Nov '24): 14

Context window

Devstral Small (Jul '25): Best: 256K
Mistral Large 2 (Nov '24): 128K

Reasoning

Devstral Small (Jul '25): No
Mistral Large 2 (Nov '24): No

Open weights

Devstral Small (Jul '25): Yes
Mistral Large 2 (Nov '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.