GPT-5.6 Luna (Medium) vs GPT-6.1 Sol (Max)
Which is better for the money: GPT-5.6 Luna (Medium) by OpenAI or GPT-6.1 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-6.1 Sol (Max) scores 26.8 points higher (51.8 vs 25.0) but costs 24× as much to run the benchmark ($1082 vs $44.3; premium vs budget cost classes). They are not alternatives at one budget: pick GPT-6.1 Sol (Max) when you need intelligence above 25.0, and GPT-5.6 Luna (Medium) when 25.0 is enough.
| Metric | GPT-5.6 Luna (Medium) | GPT-6.1 Sol (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 25.0 | 51.8 | +107.2% GPT-6.1 Sol (Max) is 2.1× more intelligent |
| Total AA cost (lower is better) | $44.32 | $1,081.55 | +2340.3% GPT-6.1 Sol (Max) is 24× more expensive |
| End-to-end time (lower is better) | 5.82s | 220.48s | +3688.3% GPT-6.1 Sol (Max) is 3688.3% slower |
| Price per 1M tokens (in / out) | $0.20 / $1.20 | $2.00 / $10.0 | |
| Input modalities | Text, Image | Text, Image |
GPT-6.1 Sol (Max) vs GPT-5.6 Luna (Medium): 107.2% more intelligence, 2340.3% more cost to run the AA benchmark, and 3688.3% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-5.6 Luna (Medium) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
- GPT-6.1 Sol (Max) is on today's frontier: nothing is both smarter and cheaper.
GPT-5.6 Luna (Medium)GPT-6.1 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-5-6-luna-medium/gpt-6-1-sol · Markdown: /api/v1/compare/gpt-5-6-luna-medium/gpt-6-1-sol?format=md · llms.txt · agent skill