Apriel-v1.5-15B-Thinker vs DeepSeek V3 (Dec '24)

Apriel-v1.5-15B-Thinker vs DeepSeek V3 (Dec '24). A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

ServiceNowApriel-v1.5-15B-ThinkerNot ranked · benchmark data missing
Intelligence
13.80
Total cost
-
DeepSeekDeepSeek V3 (Dec '24)Off the frontier
Intelligence
8.50
Total cost
$25.4
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.

MetricApriel-v1.5-15B-ThinkerDeepSeek V3 (Dec '24)Difference
Intelligence (higher is better)13.88.5−38.4% DeepSeek V3 (Dec '24) is 38.4% less intelligent
Total AA cost (lower is better)Not reported$25.37— not comparable
End-to-end time (lower is better)Not reported13.85s— not comparable
Price per 1M tokens (in / out)$0.00 / $0.00$0.32 / $0.89
Input modalitiesText, ImageText
Open this matchup in the interactive pickerApriel-v1.5-15B-Thinker: what beats itDeepSeek V3 (Dec '24): what beats it
Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/apriel-v1-5-15b-thinker/deepseek-v3 · Markdown: /api/v1/compare/apriel-v1-5-15b-thinker/deepseek-v3?format=md · llms.txt · agent skill