Model Comparator

Compare up to four models using the same criteria.

Nemotron 3.5 Super VL
NVIDIA
DeepSeek V3.1 (Non-reasoning)
DeepSeek

Differences only

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

Model Comparator
Metrics	Nemotron 3.5 Super VL NVIDIA	DeepSeek V3.1 (Non-reasoning) DeepSeek
Intelligence	13.6	Best: 13.7
Math	—	49.7
Speed	Best: 415 t/s	99 t/s
TTFT	Best: 0.71 s	1.4 s
Input · $ / 1M tokens	Best: $0.20	$0.56×2.8 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.50	$1.68×3.4 relative to the lowest price among the compared models
Context window	1M	1M
Reasoning	Yes	No
Open weights	Yes	Yes
Cost / task	$0.538	—

Intelligence

Nemotron 3.5 Super VL: 13.6
DeepSeek V3.1 (Non-reasoning): Best: 13.7

Math

Nemotron 3.5 Super VL: —
DeepSeek V3.1 (Non-reasoning): 49.7

Speed

Nemotron 3.5 Super VL: Best: 415 t/s
DeepSeek V3.1 (Non-reasoning): 99 t/s

TTFT

Nemotron 3.5 Super VL: Best: 0.71 s
DeepSeek V3.1 (Non-reasoning): 1.4 s

Input · $ / 1M tokens

Nemotron 3.5 Super VL: Best: $0.20
DeepSeek V3.1 (Non-reasoning): $0.56×2.8 relative to the lowest price among the compared models

Output · $ / 1M tokens

Nemotron 3.5 Super VL: Best: $0.50
DeepSeek V3.1 (Non-reasoning): $1.68×3.4 relative to the lowest price among the compared models

Context window

Nemotron 3.5 Super VL: 1M
DeepSeek V3.1 (Non-reasoning): 1M

Reasoning

Nemotron 3.5 Super VL: Yes
DeepSeek V3.1 (Non-reasoning): No

Open weights

Nemotron 3.5 Super VL: Yes
DeepSeek V3.1 (Non-reasoning): Yes

Cost / task

Nemotron 3.5 Super VL: $0.538
DeepSeek V3.1 (Non-reasoning): —

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.

Nemotron 3.5 Super VL13.6 · $0.275
DeepSeek V3.1 (Non-reasoning)13.7 · $0.84