GPT-5.4 mini (Xhigh) vs GPT-6 Luna (Non-reasoning)
Which is better for the money: GPT-5.4 mini (Xhigh) by OpenAI or GPT-6 Luna (Non-reasoning) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
GPT-5.4 mini (Xhigh) scores 5.6 points higher (24.1 vs 18.5) but costs 80× as much to run the benchmark ($1524 vs $19.2; premium vs budget cost classes). They are not alternatives at one budget: pick GPT-5.4 mini (Xhigh) when you need intelligence above 18.5, and GPT-6 Luna (Non-reasoning) when 18.5 is enough.
| Metric | GPT-5.4 mini (Xhigh) | GPT-6 Luna (Non-reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 24.1 | 18.5 | −23.2% GPT-6 Luna (Non-reaso… is 23.2% less intelligent |
| Total AA cost (lower is better) | $1,524.02 | $19.16 | −98.7% GPT-6 Luna (Non-reaso… is 98.7% cheaper |
| End-to-end time (lower is better) | 109.21s | 5.09s | −95.3% GPT-6 Luna (Non-reaso… is 95.3% faster |
| Price per 1M tokens (in / out) | $0.75 / $4.50 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
GPT-6 Luna (Non-reasoning) vs GPT-5.4 mini (Xhigh): 23.2% less intelligence, 98.7% less cost to run the AA benchmark, and 95.3% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-5.4 mini (Xhigh) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- GPT-6 Luna (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
GPT-5.4 mini (Xhigh)GPT-6 Luna (Non-reasoning)Today's Pareto frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gpt-5-4-mini/gpt-6-luna-non-reasoning · Markdown: /api/v1/compare/gpt-5-4-mini/gpt-6-luna-non-reasoning?format=md · llms.txt · agent skill