GPT-5.2 Codex (Xhigh) vs Granite 4.2 30B

GPT-5.2 Codex (Xhigh) vs Granite 4.2 30B. 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 Codex (Xhigh)Not ranked · benchmark data missing
Intelligence
28.50
Total cost
-
IBMGranite 4.2 30BOff the frontier
Intelligence
12.70
Total cost
$111
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 Codex (Xhigh)Granite 4.2 30BDifference
Intelligence (higher is better)28.512.7−55.4% Granite 4.2 30B is 55.4% less intelligent
Total AA cost (lower is better)Not reported$110.83— not comparable
End-to-end time (lower is better)135.26s44.22s−67.3% Granite 4.2 30B is 67.3% faster
Price per 1M tokens (in / out)$1.75 / $14.0$0.16 / $0.65
Input modalitiesText, ImageText
Open this matchup in the interactive pickerGPT-5.2 Codex (Xhigh): what beats itGranite 4.2 30B: 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-codex/granite-4-2-30b · Markdown: /api/v1/compare/gpt-5-2-codex/granite-4-2-30b?format=md · llms.txt · agent skill