Model Comparator

Compare up to four models using the same criteria.

Qwen3 1.7B (Reasoning)
Alibaba
Granite 4.0 H 1B
IBM

Differences only

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

Model Comparator
Metrics	Qwen3 1.7B (Reasoning) Alibaba	Granite 4.0 H 1B IBM	Add a model · 2/4
Intelligence	5.2	5.2
Math	Best: 38.7	6.3
Context window	32K	Best: 128K
Reasoning	Yes	No
Open weights	Yes	Yes

Intelligence

Qwen3 1.7B (Reasoning): 5.2
Granite 4.0 H 1B: 5.2

Math

Qwen3 1.7B (Reasoning): Best: 38.7
Granite 4.0 H 1B: 6.3

Context window

Qwen3 1.7B (Reasoning): 32K
Granite 4.0 H 1B: Best: 128K

Reasoning

Qwen3 1.7B (Reasoning): Yes
Granite 4.0 H 1B: No

Open weights

Qwen3 1.7B (Reasoning): Yes
Granite 4.0 H 1B: 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.