Celeris-1 vs GPT-6 Luna (Xhigh)
Which is better for the money: Celeris-1 by Celeris 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 28.3 points higher (34.6 vs 6.3) but costs 1.1× as much to run the benchmark ($66.8 vs $60.0; both mid-range class). Pick GPT-6 Luna (Xhigh) when the extra intelligence is worth the premium, otherwise Celeris-1.
| Metric | Celeris-1 | GPT-6 Luna (Xhigh) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 34.6 | +449.2% GPT-6 Luna (Xhigh) is 5.5× more intelligent |
| Total AA cost (lower is better) | $59.99 | $66.81 | +11.4% GPT-6 Luna (Xhigh) is 11.4% more expensive |
| End-to-end time (lower is better) | 0.87s | 21.27s | +2344.8% GPT-6 Luna (Xhigh) is 2344.8% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
GPT-6 Luna (Xhigh) vs Celeris-1: 449.2% more intelligence, 11.4% more cost to run the AA benchmark, and 2344.8% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Celeris-1 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Medium) scores 34.50 for $56.4.
- GPT-6 Luna (Xhigh) is on today's frontier: nothing is both smarter and cheaper.
Celeris-1GPT-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/celeris-1/gpt-6-luna-xhigh · Markdown: /api/v1/compare/celeris-1/gpt-6-luna-xhigh?format=md · llms.txt · agent skill