Model Comparator

Compare up to four models using the same criteria.

DeepSeek V4 Pro 0813 (Max)
DeepSeek
GPT-5 (High)
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 0813 (Max) DeepSeek	GPT-5 (High) OpenAI
Intelligence	Best: 23.1	23
Coding	Best: 68.8	37.8
Math	—	94.3
Agentic	41.3	—
Speed	72.7 t/s	Best: 98.2 t/s
TTFT	Best: 1.62 s	76.8 s
Input · $ / 1M tokens	$1.32×1.1 relative to the lowest price among the compared models	Best: $1.25
Output · $ / 1M tokens	Best: $3.96	$10×2.5 relative to the lowest price among the compared models
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	Yes	No
Cost / task	$1.77	—

Intelligence

DeepSeek V4 Pro 0813 (Max): Best: 23.1
GPT-5 (High): 23

Coding

DeepSeek V4 Pro 0813 (Max): Best: 68.8
GPT-5 (High): 37.8

Math

DeepSeek V4 Pro 0813 (Max): —
GPT-5 (High): 94.3

Agentic

DeepSeek V4 Pro 0813 (Max): 41.3
GPT-5 (High): —

Speed

DeepSeek V4 Pro 0813 (Max): 72.7 t/s
GPT-5 (High): Best: 98.2 t/s

TTFT

DeepSeek V4 Pro 0813 (Max): Best: 1.62 s
GPT-5 (High): 76.8 s

Input · $ / 1M tokens

DeepSeek V4 Pro 0813 (Max): $1.32×1.1 relative to the lowest price among the compared models
GPT-5 (High): Best: $1.25

Output · $ / 1M tokens

DeepSeek V4 Pro 0813 (Max): Best: $3.96
GPT-5 (High): $10×2.5 relative to the lowest price among the compared models

Context window

DeepSeek V4 Pro 0813 (Max): 1M
GPT-5 (High): 1M

Reasoning

DeepSeek V4 Pro 0813 (Max): Yes
GPT-5 (High): Yes

Open weights

DeepSeek V4 Pro 0813 (Max): Yes
GPT-5 (High): No

Cost / task

DeepSeek V4 Pro 0813 (Max): $1.77
GPT-5 (High): —

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 0813 (Max)23.1 · $1.98
GPT-5 (High)23 · $3.44