DeepSeek V3.1 (Non-reasoning) vs DeepSeek V4 Flash Vision (Max)

DeepSeek V3.1 (Non-reasoning) vs DeepSeek V4 Flash Vision (Max). A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

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.

MetricDeepSeek V3.1 (Non-reasoning)DeepSeek V4 Flash Vision (Max)Difference
Intelligence (higher is better)13.734.8+154.0% DeepSeek V4 Flash Vis… is 2.5× more intelligent
Total AA cost (lower is better)Not reported$1,081.42— not comparable
End-to-end time (lower is better)6.52s15.35s+135.4% DeepSeek V4 Flash Vis… is 135.4% slower
Price per 1M tokens (in / out)$0.56 / $1.68$0.44 / $1.32
Input modalitiesTextText, Image
Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/deepseek-v3-1/deepseek-v4-flash-vision · Markdown: /api/v1/compare/deepseek-v3-1/deepseek-v4-flash-vision?format=md · llms.txt · agent skill