Model Comparator

Compare up to four models using the same criteria.

DeepSeek R1 Distill Llama 8B
DeepSeek
DeepSeek-V2.5
DeepSeek

Differences only

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

Model Comparator
Metrics	DeepSeek R1 Distill Llama 8B DeepSeek	DeepSeek-V2.5 DeepSeek	Add a model · 2/4
Intelligence	6.5	Best: 6.6
Math	41.3	—
Context window	128K	128K
Reasoning	Yes	No
Open weights	Yes	Yes

Intelligence

DeepSeek R1 Distill Llama 8B: 6.5
DeepSeek-V2.5: Best: 6.6

Math

DeepSeek R1 Distill Llama 8B: 41.3
DeepSeek-V2.5: —

Context window

DeepSeek R1 Distill Llama 8B: 128K
DeepSeek-V2.5: 128K

Reasoning

DeepSeek R1 Distill Llama 8B: Yes
DeepSeek-V2.5: No

Open weights

DeepSeek R1 Distill Llama 8B: Yes
DeepSeek-V2.5: 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.