Model Comparator

Compare up to four models using the same criteria.

Grok 4.3 (Non-reasoning)
SpaceXSI
DeepSeek V3.1 Terminus (Non-reasoning)
DeepSeek

Differences only

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

Model Comparator
Metrics	Grok 4.3 (Non-reasoning) SpaceXSI	DeepSeek V3.1 Terminus (Non-reasoning) DeepSeek
Intelligence	Best: 14	13.9
Coding	35.2	Best: 43.5
Math	—	53.7
Agentic	Best: 14	6.8
Speed	Best: 93.9 t/s	40.8 t/s
TTFT	Best: 0.67 s	1.15 s
Input · $ / 1M tokens	$1.25×4.6 relative to the lowest price among the compared models	Best: $0.27
Output · $ / 1M tokens	$2.50×2.5 relative to the lowest price among the compared models	Best: $1
Context window	Best: 1M	128K
Reasoning	No	No
Open weights	No	Yes
Cost / task	$0.17	—

Intelligence

Grok 4.3 (Non-reasoning): Best: 14
DeepSeek V3.1 Terminus (Non-reasoning): 13.9

Coding

Grok 4.3 (Non-reasoning): 35.2
DeepSeek V3.1 Terminus (Non-reasoning): Best: 43.5

Math

Grok 4.3 (Non-reasoning): —
DeepSeek V3.1 Terminus (Non-reasoning): 53.7

Agentic

Grok 4.3 (Non-reasoning): Best: 14
DeepSeek V3.1 Terminus (Non-reasoning): 6.8

Speed

Grok 4.3 (Non-reasoning): Best: 93.9 t/s
DeepSeek V3.1 Terminus (Non-reasoning): 40.8 t/s

TTFT

Grok 4.3 (Non-reasoning): Best: 0.67 s
DeepSeek V3.1 Terminus (Non-reasoning): 1.15 s

Input · $ / 1M tokens

Grok 4.3 (Non-reasoning): $1.25×4.6 relative to the lowest price among the compared models
DeepSeek V3.1 Terminus (Non-reasoning): Best: $0.27

Output · $ / 1M tokens

Grok 4.3 (Non-reasoning): $2.50×2.5 relative to the lowest price among the compared models
DeepSeek V3.1 Terminus (Non-reasoning): Best: $1

Context window

Grok 4.3 (Non-reasoning): Best: 1M
DeepSeek V3.1 Terminus (Non-reasoning): 128K

Reasoning

Grok 4.3 (Non-reasoning): No
DeepSeek V3.1 Terminus (Non-reasoning): No

Open weights

Grok 4.3 (Non-reasoning): No
DeepSeek V3.1 Terminus (Non-reasoning): Yes

Cost / task

Grok 4.3 (Non-reasoning): $0.17
DeepSeek V3.1 Terminus (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.

Grok 4.3 (Non-reasoning)14 · $1.56
DeepSeek V3.1 Terminus (Non-reasoning)13.9 · $0.453