Model Comparator

Compare up to four models using the same criteria.

Sonar Reasoning
Perplexity
Devstral Small (May '25)
Mistral

Differences only

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

Model Comparator
Metrics	Sonar Reasoning Perplexity	Devstral Small (May '25) Mistral	Add a model · 2/4
Intelligence	8.7	8.7
Context window	127K	Best: 256K
Reasoning	Yes	No
Open weights	No	Yes

Intelligence

Sonar Reasoning: 8.7
Devstral Small (May '25): 8.7

Context window

Sonar Reasoning: 127K
Devstral Small (May '25): Best: 256K

Reasoning

Sonar Reasoning: Yes
Devstral Small (May '25): No

Open weights

Sonar Reasoning: No
Devstral Small (May '25): 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.