Celeris-1 vs GPT-5.6 Luna (High)
Which is better for the money: Celeris-1 by Celeris or GPT-5.6 Luna (High) 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-5.6 Luna (High) scores 25.8 points higher (32.1 vs 6.3) but costs 1.8× as much to run the benchmark ($108 vs $60.0; both mid-range class). Pick GPT-5.6 Luna (High) when the extra intelligence is worth the premium, otherwise Celeris-1.
| Metric | Celeris-1 | GPT-5.6 Luna (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 32.1 | +409.5% GPT-5.6 Luna (High) is 5.1× more intelligent |
| Total AA cost (lower is better) | $59.99 | $108.15 | +80.3% GPT-5.6 Luna (High) is 80.3% more expensive |
| End-to-end time (lower is better) | 0.87s | 10.89s | +1151.7% GPT-5.6 Luna (High) is 1151.7% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $0.20 / $1.20 | |
| Input modalities | Text, Image | Text, Image |
GPT-5.6 Luna (High) vs Celeris-1: 409.5% more intelligence, 80.3% more cost to run the AA benchmark, and 1151.7% 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-5.6 Luna (High) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
Celeris-1GPT-5.6 Luna (High)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-5-6-luna-high · Markdown: /api/v1/compare/celeris-1/gpt-5-6-luna-high?format=md · llms.txt · agent skill