GPT-6 Luna (Medium) vs GPT-6 Sol (Max)
Which is better for the money: GPT-6 Luna (Medium) by OpenAI or GPT-6 Sol (Max) 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 Sol (Max) scores 17.7 points higher (47.6 vs 29.9) but costs 49× as much to run the benchmark ($1536 vs $31.2; premium vs budget cost classes). They are not alternatives at one budget: pick GPT-6 Sol (Max) when you need intelligence above 29.9, and GPT-6 Luna (Medium) when 29.9 is enough.
| Metric | GPT-6 Luna (Medium) | GPT-6 Sol (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 29.9 | 47.6 | +59.2% GPT-6 Sol (Max) is 59.2% more intelligent |
| Total AA cost (lower is better) | $31.17 | $1,535.80 | +4827.2% GPT-6 Sol (Max) is 49× more expensive |
| End-to-end time (lower is better) | 8.25s | 87.14s | +956.2% GPT-6 Sol (Max) is 956.2% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $2.00 / $10.0 | |
| Input modalities | Text, Image | Text, Image |
GPT-6 Sol (Max) vs GPT-6 Luna (Medium): 59.2% more intelligence, 4827.2% more cost to run the AA benchmark, and 956.2% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (Medium) is on today's frontier: nothing is both smarter and cheaper.
- GPT-6 Sol (Max) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
GPT-6 Luna (Medium)GPT-6 Sol (Max)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-medium/gpt-6-sol · Markdown: /api/v1/compare/gpt-6-luna-medium/gpt-6-sol?format=md · llms.txt · agent skill