GPT-5.2 Codex (xhigh) vs GPT-5.3 Codex (xhigh)
GPT-5.2 Codex (xhigh) vs GPT-5.3 Codex (xhigh). 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.
| Metric | GPT-5.2 Codex (xhigh) | GPT-5.3 Codex (xhigh) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 40.1 | 44.3 | +10.5% GPT-5.3 Codex (xhigh) is 10.5% more intelligent |
| Total AA cost (lower is better) | Not reported | Not reported | — not comparable |
| End-to-end time (lower is better) | 85.21s | 109.68s | +28.7% GPT-5.3 Codex (xhigh) is 28.7% slower |
| Price per 1M tokens (in / out) | $1.75 / $14.0 | $1.75 / $14.0 | |
| Input modalities | Not reported | Not reported |
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gpt-5-2-codex/gpt-5-3-codex · Markdown: /api/v1/compare/gpt-5-2-codex/gpt-5-3-codex?format=md · llms.txt · agent skill