Claude Sonnet 4.6 (Non-reasoning, High) vs DeepSeek V4 Pro 0813 (Max)

Claude Sonnet 4.6 (Non-reasoning, High) vs DeepSeek V4 Pro 0813 (Max). A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

AnthropicClaude Sonnet 4.6 (Non-reasoning, High)Not ranked · benchmark data missing
Intelligence
24.70
Total cost
-
DeepSeekDeepSeek V4 Pro 0813 (Max)Off the frontier
Intelligence
36.00
Total cost
$1122
Verdict

Comparison incomplete

A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

MetricClaude Sonnet 4.6 (Non-reasoning, High)DeepSeek V4 Pro 0813 (Max)Difference
Intelligence (higher is better)24.736.0+45.7% DeepSeek V4 Pro 0813 … is 45.7% more intelligent
Total AA cost (lower is better)Not reported$1,122.27— not comparable
End-to-end time (lower is better)11.94s25.92s+117.1% DeepSeek V4 Pro 0813 … is 117.1% slower
Price per 1M tokens (in / out)$3.00 / $15.0$1.32 / $3.96
Input modalitiesText, ImageText
Open this matchup in the interactive pickerClaude Sonnet 4.6 (Non-reasoning, High): what beats itDeepSeek V4 Pro 0813 (Max): what beats it
Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-sonnet-4-6/deepseek-v4-pro · Markdown: /api/v1/compare/claude-sonnet-4-6/deepseek-v4-pro?format=md · llms.txt · agent skill