GPT-5.6 Luna (Non-reasoning) vs GPT-5 Codex (High)
GPT-5.6 Luna (Non-reasoning) vs GPT-5 Codex (High). 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-5.6 Luna (Non-reasoning) | GPT-5 Codex (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 15.5 | 24.9 | +60.6% GPT-5 Codex (High) is 60.6% more intelligent |
| Total AA cost (lower is better) | $22.97 | Not reported | — not comparable |
| End-to-end time (lower is better) | 4.76s | 13.09s | +175.0% GPT-5 Codex (High) is 175.0% slower |
| Price per 1M tokens (in / out) | $0.20 / $1.20 | $1.25 / $10.0 | |
| Input modalities | Text, Image | Text, Image |
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gpt-5-6-luna-non-reasoning/gpt-5-codex · Markdown: /api/v1/compare/gpt-5-6-luna-non-reasoning/gpt-5-codex?format=md · llms.txt · agent skill