Model Comparator

Compare up to four models using the same criteria.

DeepSeek-V2.5
DeepSeek
Gemini 2.0 Flash Thinking Experimental (Dec '24)
Google

Differences only

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

Model Comparator
Metrics	DeepSeek-V2.5 DeepSeek	Gemini 2.0 Flash Thinking Experimental (Dec '24) Google	Add a model · 2/4
Intelligence	6.6	6.6
Context window	128K	Best: 2M
Reasoning	No	Yes
Open weights	Yes	No

Intelligence

DeepSeek-V2.5: 6.6
Gemini 2.0 Flash Thinking Experimental (Dec '24): 6.6

Context window

DeepSeek-V2.5: 128K
Gemini 2.0 Flash Thinking Experimental (Dec '24): Best: 2M

Reasoning

DeepSeek-V2.5: No
Gemini 2.0 Flash Thinking Experimental (Dec '24): Yes

Open weights

DeepSeek-V2.5: Yes
Gemini 2.0 Flash Thinking Experimental (Dec '24): 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.