GPT-6 Luna (High) vs GPT-6 Luna (Xhigh)
Which is better for the money: GPT-6 Luna (High) by OpenAI or GPT-6 Luna (Xhigh) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
GPT-6 Luna (Xhigh) scores 1.7 points higher (34.6 vs 32.9) but costs 1.4× as much to run the benchmark ($66.8 vs $47.9; mid-range vs budget cost classes). Pick GPT-6 Luna (Xhigh) when the extra intelligence is worth the premium, otherwise GPT-6 Luna (High).
| Metric | GPT-6 Luna (High) | GPT-6 Luna (Xhigh) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 32.9 | 34.6 | +5.2% GPT-6 Luna (Xhigh) is 5.2% more intelligent |
| Total AA cost (lower is better) | $47.85 | $66.81 | +39.6% GPT-6 Luna (Xhigh) is 39.6% more expensive |
| End-to-end time (lower is better) | 12.43s | 21.27s | +71.1% GPT-6 Luna (Xhigh) is 71.1% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
GPT-6 Luna (Xhigh) vs GPT-6 Luna (High): 5.2% more intelligence, 39.6% more cost to run the AA benchmark, and 71.1% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (High) is on today's frontier: nothing is both smarter and cheaper.
- GPT-6 Luna (Xhigh) is on today's frontier: nothing is both smarter and cheaper.
GPT-6 Luna (High)GPT-6 Luna (Xhigh)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-6-luna-high/gpt-6-luna-xhigh · Markdown: /api/v1/compare/gpt-6-luna-high/gpt-6-luna-xhigh?format=md · llms.txt · agent skill