Model Comparator

Compare up to four models using the same criteria.

K2-V2 (Low)
Institute of Foundation Models
Llama 3.1 Instruct 405B
Meta

Differences only

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

Model Comparator
Metrics	K2-V2 (Low) Institute of Foundation Models	Llama 3.1 Instruct 405B Meta	Add a model · 2/4
Intelligence	7.3	7.3
Math	Best: 35.3	3
Context window	Best: 512K	128K
Reasoning	Yes	No
Open weights	Yes	Yes

Intelligence

K2-V2 (Low): 7.3
Llama 3.1 Instruct 405B: 7.3

Math

K2-V2 (Low): Best: 35.3
Llama 3.1 Instruct 405B: 3

Context window

K2-V2 (Low): Best: 512K
Llama 3.1 Instruct 405B: 128K

Reasoning

K2-V2 (Low): Yes
Llama 3.1 Instruct 405B: No

Open weights

K2-V2 (Low): Yes
Llama 3.1 Instruct 405B: 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.