Model Comparator

Compare up to four models using the same criteria.

Gemma 3n E4B Instruct Preview (May '25)
Google
Phi-3 Mini Instruct 3.8B
Microsoft

Differences only

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

Model Comparator
Metrics	Gemma 3n E4B Instruct Preview (May '25) Google	Phi-3 Mini Instruct 3.8B Microsoft	Add a model · 2/4
Intelligence	5.8	5.8
Math	—	0.3
Context window	Best: 32K	4K
Reasoning	No	No
Open weights	Yes	Yes

Intelligence

Gemma 3n E4B Instruct Preview (May '25): 5.8
Phi-3 Mini Instruct 3.8B: 5.8

Math

Gemma 3n E4B Instruct Preview (May '25): —
Phi-3 Mini Instruct 3.8B: 0.3

Context window

Gemma 3n E4B Instruct Preview (May '25): Best: 32K
Phi-3 Mini Instruct 3.8B: 4K

Reasoning

Gemma 3n E4B Instruct Preview (May '25): No
Phi-3 Mini Instruct 3.8B: No

Open weights

Gemma 3n E4B Instruct Preview (May '25): Yes
Phi-3 Mini Instruct 3.8B: 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.