Model Comparator

Compare up to four models using the same criteria.

Llama 3.1 Instruct 405B
Meta
Kimi Linear 48B A3B Instruct
Moonshot AI

Differences only

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

Model Comparator
Metrics	Llama 3.1 Instruct 405B Meta	Kimi Linear 48B A3B Instruct Moonshot AI	Add a model · 2/4
Intelligence	7.3	7.3
Math	3	Best: 36.3
Context window	128K	Best: 1M
Reasoning	No	No
Open weights	Yes	Yes

Intelligence

Llama 3.1 Instruct 405B: 7.3
Kimi Linear 48B A3B Instruct: 7.3

Math

Llama 3.1 Instruct 405B: 3
Kimi Linear 48B A3B Instruct: Best: 36.3

Context window

Llama 3.1 Instruct 405B: 128K
Kimi Linear 48B A3B Instruct: Best: 1M

Reasoning

Llama 3.1 Instruct 405B: No
Kimi Linear 48B A3B Instruct: No

Open weights

Llama 3.1 Instruct 405B: Yes
Kimi Linear 48B A3B Instruct: 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.