Claude 4.5 Sonnet (Reasoning) vs DeepSeek V3.1 (Reasoning)

Claude 4.5 Sonnet (Reasoning) vs DeepSeek V3.1 (Reasoning). A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

AnthropicClaude 4.5 Sonnet (Reasoning)Off the frontier
Intelligence
20.70
Total cost
$1501
DeepSeekDeepSeek V3.1 (Reasoning)Not ranked · benchmark data missing
Intelligence
13.50
Total cost
-
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 4.5 Sonnet (Reasoning)DeepSeek V3.1 (Reasoning)Difference
Intelligence (higher is better)20.713.5−34.8% DeepSeek V3.1 (Reason… is 34.8% less intelligent
Total AA cost (lower is better)$1,501.22Not reported— not comparable
End-to-end time (lower is better)21.58s23.64s+9.5% DeepSeek V3.1 (Reason… is 9.5% slower
Price per 1M tokens (in / out)$3.00 / $15.0$0.58 / $1.68
Input modalitiesText, ImageText
Open this matchup in the interactive pickerClaude 4.5 Sonnet (Reasoning): what beats itDeepSeek V3.1 (Reasoning): what beats it
Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-4-5-sonnet-thinking/deepseek-v3-1-reasoning · Markdown: /api/v1/compare/claude-4-5-sonnet-thinking/deepseek-v3-1-reasoning?format=md · llms.txt · agent skill