Model Comparator

Compare up to four models using the same criteria.

DeepSeek R1 Distill Qwen 1.5B
DeepSeek
Claude 2.0
Anthropic

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 1.5B DeepSeek	Claude 2.0 Anthropic	Add a model · 2/4
Intelligence	5.5	5.5
Coding	—	12.9
Math	22	—
Context window	Best: 128K	100K
Reasoning	Yes	No
Open weights	Yes	No

Intelligence

DeepSeek R1 Distill Qwen 1.5B: 5.5
Claude 2.0: 5.5

Coding

DeepSeek R1 Distill Qwen 1.5B: —
Claude 2.0: 12.9

Math

DeepSeek R1 Distill Qwen 1.5B: 22
Claude 2.0: —

Context window

DeepSeek R1 Distill Qwen 1.5B: Best: 128K
Claude 2.0: 100K

Reasoning

DeepSeek R1 Distill Qwen 1.5B: Yes
Claude 2.0: No

Open weights

DeepSeek R1 Distill Qwen 1.5B: Yes
Claude 2.0: 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.