Model Comparator

Compare up to four models using the same criteria.

o1-preview
OpenAI
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	o1-preview OpenAI	DeepSeek R1 (Jan '25) DeepSeek
Intelligence	11.4	11.4
Coding	Best: 34	24.6
Math	Best: 79.7	68
Agentic	—	1.1
Speed	—	150 t/s
TTFT	—	1.09 s
Input · $ / 1M tokens	$16.50×8.3 relative to the lowest price among the compared models	Best: $2
Output · $ / 1M tokens	$66×16.5 relative to the lowest price among the compared models	Best: $4
Context window	128K	128K
Reasoning	Yes	Yes
Open weights	No	Yes
Cost / task	—	$0.262

Intelligence

o1-preview: 11.4
DeepSeek R1 (Jan '25): 11.4

Coding

o1-preview: Best: 34
DeepSeek R1 (Jan '25): 24.6

Math

o1-preview: Best: 79.7
DeepSeek R1 (Jan '25): 68

Agentic

o1-preview: —
DeepSeek R1 (Jan '25): 1.1

Speed

o1-preview: —
DeepSeek R1 (Jan '25): 150 t/s

TTFT

o1-preview: —
DeepSeek R1 (Jan '25): 1.09 s

Input · $ / 1M tokens

o1-preview: $16.50×8.3 relative to the lowest price among the compared models
DeepSeek R1 (Jan '25): Best: $2

Output · $ / 1M tokens

o1-preview: $66×16.5 relative to the lowest price among the compared models
DeepSeek R1 (Jan '25): Best: $4

Context window

o1-preview: 128K
DeepSeek R1 (Jan '25): 128K

Reasoning

o1-preview: Yes
DeepSeek R1 (Jan '25): Yes

Open weights

o1-preview: No
DeepSeek R1 (Jan '25): Yes

Cost / task

o1-preview: —
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.

o1-preview11.4 · $28.88
DeepSeek R1 (Jan '25)11.4 · $2.50