FR

Model Comparator

Compare up to four models using the same criteria.

Differences only

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

Model Comparator
Metrics	Llama 3.3 Nemotron Super 49B v1 (Reasoning) NVIDIA	Devstral Medium Mistral	Add a model · 2/4
Intelligence	8.9	Best: 9
Math	Best: 54.7	4.7
Context window	128K	Best: 256K
Reasoning	Yes	No
Open weights	Yes	No

Intelligence

Llama 3.3 Nemotron Super 49B v1 (Reasoning): 8.9
Devstral Medium: Best: 9

Math

Llama 3.3 Nemotron Super 49B v1 (Reasoning): Best: 54.7
Devstral Medium: 4.7

Context window

Llama 3.3 Nemotron Super 49B v1 (Reasoning): 128K
Devstral Medium: Best: 256K

Reasoning

Llama 3.3 Nemotron Super 49B v1 (Reasoning): Yes
Devstral Medium: No

Open weights

Llama 3.3 Nemotron Super 49B v1 (Reasoning): Yes
Devstral Medium: No

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.