Model Comparator

Compare up to four models using the same criteria.

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

Differences only

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

Model Comparator
Metrics	Claude Sonnet 4.6 (batch) Anthropic	DeepSeek V4 Pro 0424 (Max) DeepSeek
Intelligence	30.1	Best: 30.4
Coding	Best: 63	59.4
Agentic	Best: 31.8	26.3
Speed	—	88 t/s
TTFT	—	1.45 s
Input · $ / 1M tokens	—	$1.31
Output · $ / 1M tokens	—	$3.14
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	—	Yes
Cost / task	—	$0.122

Intelligence

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

Coding

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

Agentic

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

Speed

Claude Sonnet 4.6 (batch): —
DeepSeek V4 Pro 0424 (Max): 88 t/s

TTFT

Claude Sonnet 4.6 (batch): —
DeepSeek V4 Pro 0424 (Max): 1.45 s

Input · $ / 1M tokens

Claude Sonnet 4.6 (batch): —
DeepSeek V4 Pro 0424 (Max): $1.31

Output · $ / 1M tokens

Claude Sonnet 4.6 (batch): —
DeepSeek V4 Pro 0424 (Max): $3.14

Context window

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

Reasoning

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

Open weights

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

Cost / task

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

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).