Model Comparator

Compare up to four models using the same criteria.

Gemini 2.0 Pro Experimental (Feb '25)
Google
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	Gemini 2.0 Pro Experimental (Feb '25) Google	Devstral Small (May '25) Mistral	Add a model · 2/4
Intelligence	8.7	8.7
Coding	25.5	—
Context window	Best: 2M	256K
Reasoning	No	No
Open weights	No	Yes

Intelligence

Gemini 2.0 Pro Experimental (Feb '25): 8.7
Devstral Small (May '25): 8.7

Coding

Gemini 2.0 Pro Experimental (Feb '25): 25.5
Devstral Small (May '25): —

Context window

Gemini 2.0 Pro Experimental (Feb '25): Best: 2M
Devstral Small (May '25): 256K

Reasoning

Gemini 2.0 Pro Experimental (Feb '25): No
Devstral Small (May '25): No

Open weights

Gemini 2.0 Pro Experimental (Feb '25): 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.