DeepSeek-V2.5 (Dec '24) vs Devstral Small (Jul '25)

DeepSeek-V2.5 (Dec '24) vs Devstral Small (Jul '25). 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-V2.5 (Dec '24)Devstral Small (Jul '25)Difference
Intelligence (higher is better)6.67.6+15.2% Devstral Small (Jul '… is 15.2% more intelligent
Total AA cost (lower is better)Not reportedNot reported— not comparable
End-to-end time (lower is better)Not reportedNot reported— not comparable
Input modalitiesTextText
Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/deepseek-v2-5/devstral-small · Markdown: /api/v1/compare/deepseek-v2-5/devstral-small?format=md · llms.txt · agent skill