Model Comparator

Compare up to four models using the same criteria.

Grok 2 (Dec '24)
SpaceXSI
Olmo 3.1 32B Think
Allen Institute for AI

Differences only

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

Model Comparator
Metrics	Grok 2 (Dec '24) SpaceXSI	Olmo 3.1 32B Think Allen Institute for AI	Add a model · 2/4
Intelligence	7.1	7.1
Math	—	77.3
Context window	Best: 131K	66K
Reasoning	No	Yes
Open weights	Yes	Yes

Intelligence

Grok 2 (Dec '24): 7.1
Olmo 3.1 32B Think: 7.1

Math

Grok 2 (Dec '24): —
Olmo 3.1 32B Think: 77.3

Context window

Grok 2 (Dec '24): Best: 131K
Olmo 3.1 32B Think: 66K

Reasoning

Grok 2 (Dec '24): No
Olmo 3.1 32B Think: Yes

Open weights

Grok 2 (Dec '24): Yes
Olmo 3.1 32B Think: 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.