Model Comparator

Compare up to four models using the same criteria.

DeepSeek V4 Pro 0424 (Non-reasoning)
DeepSeek
GPT-5.4 nano (Xhigh)
OpenAI

Differences only

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

Model Comparator
Metrics	DeepSeek V4 Pro 0424 (Non-reasoning) DeepSeek	GPT-5.4 nano (Xhigh) OpenAI
Intelligence	Best: 20.8	20.7
Coding	—	56.1
Agentic	—	16
Speed	95.1 t/s	Best: 166 t/s
TTFT	Best: 1.58 s	81 s
Input · $ / 1M tokens	$0.435×2.2 relative to the lowest price among the compared models	Best: $0.20
Output · $ / 1M tokens	Best: $0.87	$1.25×1.4 relative to the lowest price among the compared models
Context window	Best: 1M	400K
Reasoning	No	Yes
Open weights	Yes	No
Cost / task	—	$0.183

Intelligence

DeepSeek V4 Pro 0424 (Non-reasoning): Best: 20.8
GPT-5.4 nano (Xhigh): 20.7

Coding

DeepSeek V4 Pro 0424 (Non-reasoning): —
GPT-5.4 nano (Xhigh): 56.1

Agentic

DeepSeek V4 Pro 0424 (Non-reasoning): —
GPT-5.4 nano (Xhigh): 16

Speed

DeepSeek V4 Pro 0424 (Non-reasoning): 95.1 t/s
GPT-5.4 nano (Xhigh): Best: 166 t/s

TTFT

DeepSeek V4 Pro 0424 (Non-reasoning): Best: 1.58 s
GPT-5.4 nano (Xhigh): 81 s

Input · $ / 1M tokens

DeepSeek V4 Pro 0424 (Non-reasoning): $0.435×2.2 relative to the lowest price among the compared models
GPT-5.4 nano (Xhigh): Best: $0.20

Output · $ / 1M tokens

DeepSeek V4 Pro 0424 (Non-reasoning): Best: $0.87
GPT-5.4 nano (Xhigh): $1.25×1.4 relative to the lowest price among the compared models

Context window

DeepSeek V4 Pro 0424 (Non-reasoning): Best: 1M
GPT-5.4 nano (Xhigh): 400K

Reasoning

DeepSeek V4 Pro 0424 (Non-reasoning): No
GPT-5.4 nano (Xhigh): Yes

Open weights

DeepSeek V4 Pro 0424 (Non-reasoning): Yes
GPT-5.4 nano (Xhigh): No

Cost / task

DeepSeek V4 Pro 0424 (Non-reasoning): —
GPT-5.4 nano (Xhigh): $0.183

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 V4 Pro 0424 (Non-reasoning)20.8 · $0.544
GPT-5.4 nano (Xhigh)20.7 · $0.463