GPT-6 Luna (Low) vs GPT-6 Luna (Medium)
Which is better for the money: GPT-6 Luna (Low) by OpenAI or GPT-6 Luna (Medium) 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 (Medium) scores 8.4 points higher (29.9 vs 21.5) but costs 2.9× as much to run the benchmark ($31.2 vs $10.6; both budget class). Pick GPT-6 Luna (Medium) when the extra intelligence is worth the premium, otherwise GPT-6 Luna (Low).
| Metric | GPT-6 Luna (Low) | GPT-6 Luna (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 21.5 | 29.9 | +39.1% GPT-6 Luna (Medium) is 39.1% more intelligent |
| Total AA cost (lower is better) | $10.63 | $31.17 | +193.2% GPT-6 Luna (Medium) is 2.9× more expensive |
| End-to-end time (lower is better) | 6.60s | 8.25s | +25.0% GPT-6 Luna (Medium) is 25.0% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
GPT-6 Luna (Medium) vs GPT-6 Luna (Low): 39.1% more intelligence, 193.2% more cost to run the AA benchmark, and 25.0% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (Low) is on today's frontier: nothing is both smarter and cheaper.
- GPT-6 Luna (Medium) is on today's frontier: nothing is both smarter and cheaper.
GPT-6 Luna (Low)GPT-6 Luna (Medium)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-low/gpt-6-luna-medium · Markdown: /api/v1/compare/gpt-6-luna-low/gpt-6-luna-medium?format=md · llms.txt · agent skill