Model Comparator

Compare up to four models using the same criteria.

DeepSeek R1 Distill Qwen 14B
DeepSeek
Gemma 4 E2B (Reasoning)
Google

Differences only

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

Model Comparator
Metrics	DeepSeek R1 Distill Qwen 14B DeepSeek	Gemma 4 E2B (Reasoning) Google	Add a model · 2/4
Intelligence	7.8	7.8
Coding	—	7.2
Math	55.7	—
Context window	128K	128K
Reasoning	Yes	Yes
Open weights	Yes	Yes

Intelligence

DeepSeek R1 Distill Qwen 14B: 7.8
Gemma 4 E2B (Reasoning): 7.8

Coding

DeepSeek R1 Distill Qwen 14B: —
Gemma 4 E2B (Reasoning): 7.2

Math

DeepSeek R1 Distill Qwen 14B: 55.7
Gemma 4 E2B (Reasoning): —

Context window

DeepSeek R1 Distill Qwen 14B: 128K
Gemma 4 E2B (Reasoning): 128K

Reasoning

DeepSeek R1 Distill Qwen 14B: Yes
Gemma 4 E2B (Reasoning): Yes

Open weights

DeepSeek R1 Distill Qwen 14B: Yes
Gemma 4 E2B (Reasoning): 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.