Model Comparator

Compare up to four models using the same criteria.

DeepSeek V3.2 Speciale
DeepSeek
Grok 3 mini Reasoning (High)
SpaceXSI

Differences only

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

Model Comparator
Metrics	DeepSeek V3.2 Speciale DeepSeek	Grok 3 mini Reasoning (High) SpaceXSI
Intelligence	14.5	Best: 14.6
Math	Best: 96.7	84.7
Speed	—	65.3 t/s
TTFT	—	1.74 s
Input · $ / 1M tokens	—	$0.30
Output · $ / 1M tokens	—	$0.50
Context window	128K	Best: 1M
Reasoning	Yes	Yes
Open weights	Yes	No

Intelligence

DeepSeek V3.2 Speciale: 14.5
Grok 3 mini Reasoning (High): Best: 14.6

Math

DeepSeek V3.2 Speciale: Best: 96.7
Grok 3 mini Reasoning (High): 84.7

Speed

DeepSeek V3.2 Speciale: —
Grok 3 mini Reasoning (High): 65.3 t/s

TTFT

DeepSeek V3.2 Speciale: —
Grok 3 mini Reasoning (High): 1.74 s

Input · $ / 1M tokens

DeepSeek V3.2 Speciale: —
Grok 3 mini Reasoning (High): $0.30

Output · $ / 1M tokens

DeepSeek V3.2 Speciale: —
Grok 3 mini Reasoning (High): $0.50

Context window

DeepSeek V3.2 Speciale: 128K
Grok 3 mini Reasoning (High): Best: 1M

Reasoning

DeepSeek V3.2 Speciale: Yes
Grok 3 mini Reasoning (High): Yes

Open weights

DeepSeek V3.2 Speciale: Yes
Grok 3 mini Reasoning (High): 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.

Grok 3 mini Reasoning (High)14.6 · $0.35

Not plotted for lack of data on these axes: DeepSeek V3.2 Speciale.