Model Comparator

Compare up to four models using the same criteria.

DeepSeek V3 (Dec '24)
DeepSeek
GPT-4o (2024-11-20)
OpenAI

Differences only

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

Model Comparator
Metrics	DeepSeek V3 (Dec '24) DeepSeek	GPT-4o (2024-11-20) OpenAI
Intelligence	Best: 8.5	8.4
Coding	23	—
Math	26	—
Agentic	0.8	—
Speed	37 t/s	—
TTFT	1.4 s	—
Input · $ / 1M tokens	Best: $0.32	$2.50×7.8 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.89	$10×11.2 relative to the lowest price among the compared models
Context window	128K	128K
Reasoning	No	No
Open weights	Yes	No
Cost / task	$0.0198	—

Intelligence

DeepSeek V3 (Dec '24): Best: 8.5
GPT-4o (2024-11-20): 8.4

Coding

DeepSeek V3 (Dec '24): 23
GPT-4o (2024-11-20): —

Math

DeepSeek V3 (Dec '24): 26
GPT-4o (2024-11-20): —

Agentic

DeepSeek V3 (Dec '24): 0.8
GPT-4o (2024-11-20): —

Speed

DeepSeek V3 (Dec '24): 37 t/s
GPT-4o (2024-11-20): —

TTFT

DeepSeek V3 (Dec '24): 1.4 s
GPT-4o (2024-11-20): —

Input · $ / 1M tokens

DeepSeek V3 (Dec '24): Best: $0.32
GPT-4o (2024-11-20): $2.50×7.8 relative to the lowest price among the compared models

Output · $ / 1M tokens

DeepSeek V3 (Dec '24): Best: $0.89
GPT-4o (2024-11-20): $10×11.2 relative to the lowest price among the compared models

Context window

DeepSeek V3 (Dec '24): 128K
GPT-4o (2024-11-20): 128K

Reasoning

DeepSeek V3 (Dec '24): No
GPT-4o (2024-11-20): No

Open weights

DeepSeek V3 (Dec '24): Yes
GPT-4o (2024-11-20): No

Cost / task

DeepSeek V3 (Dec '24): $0.0198
GPT-4o (2024-11-20): —

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 V3 (Dec '24)8.5 · $0.463
GPT-4o (2024-11-20)8.4 · $4.38