Model Comparator

Compare up to four models using the same criteria.

Devstral Small (May '25)
Mistral
Gemini 2.0 Pro Experimental (Feb '25)
Google

Differences only

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

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

Intelligence

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

Coding

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

Context window

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

Reasoning

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

Open weights

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

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.