Model Comparator

Compare up to four models using the same criteria.

DeepSeek R1 0528 (May '25)
DeepSeek
GPT-5 nano (High)
OpenAI

Differences only

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

Model Comparator
Metrics	DeepSeek R1 0528 (May '25) DeepSeek	GPT-5 nano (High) OpenAI
Intelligence	Best: 13.1	13
Coding	24.6	—
Math	76	Best: 83.7
Agentic	1.1	—
Speed	32.8 t/s	Best: 157 t/s
TTFT	Best: 1.05 s	61.2 s
Input · $ / 1M tokens	$1.35×27 relative to the lowest price among the compared models	Best: $0.050
Output · $ / 1M tokens	$3×7.5 relative to the lowest price among the compared models	Best: $0.40
Context window	128K	Best: 400K
Reasoning	Yes	Yes
Open weights	Yes	No

Intelligence

DeepSeek R1 0528 (May '25): Best: 13.1
GPT-5 nano (High): 13

Coding

DeepSeek R1 0528 (May '25): 24.6
GPT-5 nano (High): —

Math

DeepSeek R1 0528 (May '25): 76
GPT-5 nano (High): Best: 83.7

Agentic

DeepSeek R1 0528 (May '25): 1.1
GPT-5 nano (High): —

Speed

DeepSeek R1 0528 (May '25): 32.8 t/s
GPT-5 nano (High): Best: 157 t/s

TTFT

DeepSeek R1 0528 (May '25): Best: 1.05 s
GPT-5 nano (High): 61.2 s

Input · $ / 1M tokens

DeepSeek R1 0528 (May '25): $1.35×27 relative to the lowest price among the compared models
GPT-5 nano (High): Best: $0.050

Output · $ / 1M tokens

DeepSeek R1 0528 (May '25): $3×7.5 relative to the lowest price among the compared models
GPT-5 nano (High): Best: $0.40

Context window

DeepSeek R1 0528 (May '25): 128K
GPT-5 nano (High): Best: 400K

Reasoning

DeepSeek R1 0528 (May '25): Yes
GPT-5 nano (High): Yes

Open weights

DeepSeek R1 0528 (May '25): Yes
GPT-5 nano (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.

DeepSeek R1 0528 (May '25)13.1 · $1.76
GPT-5 nano (High)13 · $0.138