Model Comparator

Compare up to four models using the same criteria.

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
NVIDIA
GPT-4
OpenAI

Differences only

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

Model Comparator
Metrics	NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) NVIDIA	GPT-4 OpenAI
Intelligence	Best: 6.8	6.7
Coding	—	13.1
Math	13.3	—
Speed	250 t/s	—
TTFT	0.52 s	—
Input · $ / 1M tokens	Best: $0.050	$30×600 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.20	$60×300 relative to the lowest price among the compared models
Context window	Best: 1M	8K
Reasoning	No	No
Open weights	Yes	No

Intelligence

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning): Best: 6.8
GPT-4: 6.7

Coding

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning): —
GPT-4: 13.1

Math

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning): 13.3
GPT-4: —

Speed

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning): 250 t/s
GPT-4: —

TTFT

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning): 0.52 s
GPT-4: —

Input · $ / 1M tokens

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning): Best: $0.050
GPT-4: $30×600 relative to the lowest price among the compared models

Output · $ / 1M tokens

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning): Best: $0.20
GPT-4: $60×300 relative to the lowest price among the compared models

Context window

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning): Best: 1M
GPT-4: 8K

Reasoning

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning): No
GPT-4: No

Open weights

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning): Yes
GPT-4: No

Each reasoning level remains a separate configuration.

Score and cost

Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)6.8 · $0.088
GPT-46.7 · $37.50