Model Comparator

Compare up to four models using the same criteria.

DeepSeek V4.1 Flash (Non-reasoning)
DeepSeek
Claude Sonnet 4.6 (Non-reasoning, High)
Anthropic

Differences only

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

Model Comparator
Metrics	DeepSeek V4.1 Flash (Non-reasoning) DeepSeek	Claude Sonnet 4.6 (Non-reasoning, High) Anthropic
Intelligence	24.7	24.7
Coding	—	63
Agentic	—	31.8
Speed	Best: 248 t/s	48.7 t/s
TTFT	Best: 0.93 s	1.04 s
Input · $ / 1M tokens	Best: $0.30	$3×10 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $1.20	$15×12.5 relative to the lowest price among the compared models
Context window	1M	1M
Reasoning	No	No
Open weights	Yes	No
Cost / task	$0.234	—

Intelligence

DeepSeek V4.1 Flash (Non-reasoning): 24.7
Claude Sonnet 4.6 (Non-reasoning, High): 24.7

Coding

DeepSeek V4.1 Flash (Non-reasoning): —
Claude Sonnet 4.6 (Non-reasoning, High): 63

Agentic

DeepSeek V4.1 Flash (Non-reasoning): —
Claude Sonnet 4.6 (Non-reasoning, High): 31.8

Speed

DeepSeek V4.1 Flash (Non-reasoning): Best: 248 t/s
Claude Sonnet 4.6 (Non-reasoning, High): 48.7 t/s

TTFT

DeepSeek V4.1 Flash (Non-reasoning): Best: 0.93 s
Claude Sonnet 4.6 (Non-reasoning, High): 1.04 s

Input · $ / 1M tokens

DeepSeek V4.1 Flash (Non-reasoning): Best: $0.30
Claude Sonnet 4.6 (Non-reasoning, High): $3×10 relative to the lowest price among the compared models

Output · $ / 1M tokens

DeepSeek V4.1 Flash (Non-reasoning): Best: $1.20
Claude Sonnet 4.6 (Non-reasoning, High): $15×12.5 relative to the lowest price among the compared models

Context window

DeepSeek V4.1 Flash (Non-reasoning): 1M
Claude Sonnet 4.6 (Non-reasoning, High): 1M

Reasoning

DeepSeek V4.1 Flash (Non-reasoning): No
Claude Sonnet 4.6 (Non-reasoning, High): No

Open weights

DeepSeek V4.1 Flash (Non-reasoning): Yes
Claude Sonnet 4.6 (Non-reasoning, High): No

Cost / task

DeepSeek V4.1 Flash (Non-reasoning): $0.234
Claude Sonnet 4.6 (Non-reasoning, 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 V4.1 Flash (Non-reasoning)24.7 · $0.525
Claude Sonnet 4.6 (Non-reasoning, High)24.7 · $6