Model Comparator

Compare up to four models using the same criteria.

LFM2.5-2.6B
Liquid AI
DeepSeek R1 Distill Qwen 32B
DeepSeek

Differences only

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

Model Comparator
Metrics	LFM2.5-2.6B Liquid AI	DeepSeek R1 Distill Qwen 32B DeepSeek	Add a model · 2/4
Intelligence	8.4	8.4
Coding	7.7	—
Math	—	63
Context window	128K	128K
Reasoning	Yes	Yes
Open weights	Yes	Yes

Intelligence

LFM2.5-2.6B: 8.4
DeepSeek R1 Distill Qwen 32B: 8.4

Coding

LFM2.5-2.6B: 7.7
DeepSeek R1 Distill Qwen 32B: —

Math

LFM2.5-2.6B: —
DeepSeek R1 Distill Qwen 32B: 63

Context window

LFM2.5-2.6B: 128K
DeepSeek R1 Distill Qwen 32B: 128K

Reasoning

LFM2.5-2.6B: Yes
DeepSeek R1 Distill Qwen 32B: Yes

Open weights

LFM2.5-2.6B: Yes
DeepSeek R1 Distill Qwen 32B: 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.