Model Comparator

Compare up to four models using the same criteria.

Grok 4.1 Fast (Non-reasoning)
SpaceXSI
DeepSeek R1 (Jan '25)
DeepSeek

Differences only

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

Model Comparator
Metrics	Grok 4.1 Fast (Non-reasoning) SpaceXSI	DeepSeek R1 (Jan '25) DeepSeek
Intelligence	11.3	Best: 11.4
Coding	—	24.6
Math	34.3	Best: 68
Agentic	—	1.1
Speed	—	148 t/s
TTFT	—	1.09 s
Input · $ / 1M tokens	—	$2
Output · $ / 1M tokens	—	$4
Context window	Best: 2M	128K
Reasoning	No	Yes
Open weights	No	Yes
Cost / task	—	$0.262

Intelligence

Grok 4.1 Fast (Non-reasoning): 11.3
DeepSeek R1 (Jan '25): Best: 11.4

Coding

Grok 4.1 Fast (Non-reasoning): —
DeepSeek R1 (Jan '25): 24.6

Math

Grok 4.1 Fast (Non-reasoning): 34.3
DeepSeek R1 (Jan '25): Best: 68

Agentic

Grok 4.1 Fast (Non-reasoning): —
DeepSeek R1 (Jan '25): 1.1

Speed

Grok 4.1 Fast (Non-reasoning): —
DeepSeek R1 (Jan '25): 148 t/s

TTFT

Grok 4.1 Fast (Non-reasoning): —
DeepSeek R1 (Jan '25): 1.09 s

Input · $ / 1M tokens

Grok 4.1 Fast (Non-reasoning): —
DeepSeek R1 (Jan '25): $2

Output · $ / 1M tokens

Grok 4.1 Fast (Non-reasoning): —
DeepSeek R1 (Jan '25): $4

Context window

Grok 4.1 Fast (Non-reasoning): Best: 2M
DeepSeek R1 (Jan '25): 128K

Reasoning

Grok 4.1 Fast (Non-reasoning): No
DeepSeek R1 (Jan '25): Yes

Open weights

Grok 4.1 Fast (Non-reasoning): No
DeepSeek R1 (Jan '25): Yes

Cost / task

Grok 4.1 Fast (Non-reasoning): —
DeepSeek R1 (Jan '25): $0.262

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.

DeepSeek R1 (Jan '25)11.4 · $0.262

Not plotted for lack of data on these axes: Grok 4.1 Fast (Non-reasoning).