Model Comparator

Compare up to four models using the same criteria.

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

Differences only

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

Model Comparator
Metrics	GPT-5 nano (High) OpenAI	DeepSeek R1 0528 (May '25) DeepSeek
Intelligence	13	Best: 13.1
Coding	—	24.6
Math	Best: 83.7	76
Agentic	—	1.1
Speed	Best: 159 t/s	31.9 t/s
TTFT	70.7 s	Best: 1.04 s
Input · $ / 1M tokens	Best: $0.050	$1.35×27 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.40	$3×7.5 relative to the lowest price among the compared models
Context window	Best: 400K	128K
Reasoning	Yes	Yes
Open weights	No	Yes

Intelligence

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

Coding

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

Math

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

Agentic

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

Speed

GPT-5 nano (High): Best: 159 t/s
DeepSeek R1 0528 (May '25): 31.9 t/s

TTFT

GPT-5 nano (High): 70.7 s
DeepSeek R1 0528 (May '25): Best: 1.04 s

Input · $ / 1M tokens

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

Output · $ / 1M tokens

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

Context window

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

Reasoning

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

Open weights

GPT-5 nano (High): No
DeepSeek R1 0528 (May '25): Yes

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.

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