GPT-5.2 (Non-reasoning) vs GPT-5.4 (Low)

GPT-5.2 (Non-reasoning) vs GPT-5.4 (Low). A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

OpenAIGPT-5.2 (Non-reasoning)Not ranked · benchmark data missing
Intelligence
17.00
Total cost
-
OpenAIGPT-5.4 (Low)Not ranked · benchmark data missing
Intelligence
27.60
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.

MetricGPT-5.2 (Non-reasoning)GPT-5.4 (Low)Difference
Intelligence (higher is better)17.027.6+62.4% GPT-5.4 (Low) is 62.4% more intelligent
Total AA cost (lower is better)Not reportedNot reported— not comparable
End-to-end time (lower is better)8.19s9.06s+10.6% GPT-5.4 (Low) is 10.6% slower
Price per 1M tokens (in / out)$1.75 / $14.0$2.50 / $15.0
Input modalitiesText, ImageText, Image
Open this matchup in the interactive pickerGPT-5.2 (Non-reasoning): what beats itGPT-5.4 (Low): what beats it
Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gpt-5-2-non-reasoning/gpt-5-4-low · Markdown: /api/v1/compare/gpt-5-2-non-reasoning/gpt-5-4-low?format=md · llms.txt · agent skill