Claude Opus 4.6 (Non-reasoning, High) vs DeepSeek V3.2 (Non-reasoning)

Claude Opus 4.6 (Non-reasoning, High) vs DeepSeek V3.2 (Non-reasoning). A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

AnthropicClaude Opus 4.6 (Non-reasoning, High)Not ranked · benchmark data missing
Intelligence
26.40
Total cost
-
DeepSeekDeepSeek V3.2 (Non-reasoning)Not ranked · benchmark data missing
Intelligence
16.00
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 Opus 4.6 (Non-reasoning, High)DeepSeek V3.2 (Non-reasoning)Difference
Intelligence (higher is better)26.416.0−39.4% DeepSeek V3.2 (Non-re… is 39.4% less intelligent
Total AA cost (lower is better)Not reportedNot reported— not comparable
End-to-end time (lower is better)15.11sNot reported— not comparable
Price per 1M tokens (in / out)$5.00 / $25.0$0.28 / $0.42
Input modalitiesText, ImageText
Open this matchup in the interactive pickerClaude Opus 4.6 (Non-reasoning, High): what beats itDeepSeek V3.2 (Non-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-opus-4-6/deepseek-v3-2 · Markdown: /api/v1/compare/claude-opus-4-6/deepseek-v3-2?format=md · llms.txt · agent skill