GPT-5.6 Luna (High) vs GPT-6.1 Sol (Medium)
Which is better for the money: GPT-5.6 Luna (High) by OpenAI or GPT-6.1 Sol (Medium) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
GPT-6.1 Sol (Medium) scores 15.7 points higher (47.8 vs 32.1) but costs 3.3× as much to run the benchmark ($361 vs $108; both mid-range class). They are not alternatives at one budget: pick GPT-6.1 Sol (Medium) when you need intelligence above 32.1, and GPT-5.6 Luna (High) when 32.1 is enough.
| Metric | GPT-5.6 Luna (High) | GPT-6.1 Sol (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 32.1 | 47.8 | +48.9% GPT-6.1 Sol (Medium) is 48.9% more intelligent |
| Total AA cost (lower is better) | $108.15 | $361.37 | +234.1% GPT-6.1 Sol (Medium) is 3.3× more expensive |
| End-to-end time (lower is better) | 16.71s | 13.94s | −16.6% GPT-6.1 Sol (Medium) is 16.6% faster |
| Price per 1M tokens (in / out) | $0.20 / $1.20 | $2.00 / $10.0 | |
| Input modalities | Text, Image | Text, Image |
GPT-6.1 Sol (Medium) vs GPT-5.6 Luna (High): 48.9% more intelligence, 234.1% more cost to run the AA benchmark, and 16.6% faster end-to-end.
Today's Pareto frontier
Against the frontier
- 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.
- GPT-6.1 Sol (Medium) is on today's frontier: nothing is both smarter and cheaper.
GPT-5.6 Luna (High)GPT-6.1 Sol (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-5-6-luna-high/gpt-6-1-sol-medium · Markdown: /api/v1/compare/gpt-5-6-luna-high/gpt-6-1-sol-medium?format=md · llms.txt · agent skill