Model Comparator

Compare up to four models using the same criteria.

DeepSeek V4 Pro 0424 (Max)
DeepSeek
Claude Sonnet 4.6 (batch)
Anthropic

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 (Max) DeepSeek	Claude Sonnet 4.6 (batch) Anthropic
Intelligence	Best: 30.4	30.1
Coding	59.4	Best: 63
Agentic	26.3	Best: 31.8
Speed	83.8 t/s	—
TTFT	1.79 s	—
Input · $ / 1M tokens	$0.435	—
Output · $ / 1M tokens	$0.87	—
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	Yes	—
Cost / task	$0.122	—

Intelligence

DeepSeek V4 Pro 0424 (Max): Best: 30.4
Claude Sonnet 4.6 (batch): 30.1

Coding

DeepSeek V4 Pro 0424 (Max): 59.4
Claude Sonnet 4.6 (batch): Best: 63

Agentic

DeepSeek V4 Pro 0424 (Max): 26.3
Claude Sonnet 4.6 (batch): Best: 31.8

Speed

DeepSeek V4 Pro 0424 (Max): 83.8 t/s
Claude Sonnet 4.6 (batch): —

TTFT

DeepSeek V4 Pro 0424 (Max): 1.79 s
Claude Sonnet 4.6 (batch): —

Input · $ / 1M tokens

DeepSeek V4 Pro 0424 (Max): $0.435
Claude Sonnet 4.6 (batch): —

Output · $ / 1M tokens

DeepSeek V4 Pro 0424 (Max): $0.87
Claude Sonnet 4.6 (batch): —

Context window

DeepSeek V4 Pro 0424 (Max): 1M
Claude Sonnet 4.6 (batch): 1M

Reasoning

DeepSeek V4 Pro 0424 (Max): Yes
Claude Sonnet 4.6 (batch): Yes

Open weights

DeepSeek V4 Pro 0424 (Max): Yes
Claude Sonnet 4.6 (batch): —

Cost / task

DeepSeek V4 Pro 0424 (Max): $0.122
Claude Sonnet 4.6 (batch): —

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 (Max)30.4 · $0.122

Not plotted for lack of data on these axes: Claude Sonnet 4.6 (batch).