Model Comparator

Compare up to four models using the same criteria.

GPT-5 (batch)
OpenAI
DeepSeek V4 Pro 0813 (Max)
DeepSeek

Differences only

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

Model Comparator
Metrics	GPT-5 (batch) OpenAI	DeepSeek V4 Pro 0813 (Max) DeepSeek
Intelligence	23	Best: 23.1
Coding	37.8	Best: 68.8
Agentic	—	41.3
Speed	—	72.7 t/s
TTFT	—	1.62 s
Input · $ / 1M tokens	Best: $0.625	$1.32×2.1 relative to the lowest price among the compared models
Output · $ / 1M tokens	$5×1.3 relative to the lowest price among the compared models	Best: $3.96
Context window	400K	Best: 1M
Reasoning	Yes	Yes
Open weights	—	Yes
Cost / task	—	$1.77

Intelligence

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

Coding

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

Agentic

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

Speed

GPT-5 (batch): —
DeepSeek V4 Pro 0813 (Max): 72.7 t/s

TTFT

GPT-5 (batch): —
DeepSeek V4 Pro 0813 (Max): 1.62 s

Input · $ / 1M tokens

GPT-5 (batch): Best: $0.625
DeepSeek V4 Pro 0813 (Max): $1.32×2.1 relative to the lowest price among the compared models

Output · $ / 1M tokens

GPT-5 (batch): $5×1.3 relative to the lowest price among the compared models
DeepSeek V4 Pro 0813 (Max): Best: $3.96

Context window

GPT-5 (batch): 400K
DeepSeek V4 Pro 0813 (Max): Best: 1M

Reasoning

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

Open weights

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

Cost / task

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

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 (batch)23 · $1.72
DeepSeek V4 Pro 0813 (Max)23.1 · $1.98