GPT-6.1 Sol (High) vs GPT-6 Luna (Low)
Which is better for the money: GPT-6.1 Sol (High) by OpenAI or GPT-6 Luna (Low) 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 (High) scores 28.7 points higher (50.2 vs 21.5) but costs 49× as much to run the benchmark ($521 vs $10.6; premium vs budget cost classes). They are not alternatives at one budget: pick GPT-6.1 Sol (High) when you need intelligence above 21.5, and GPT-6 Luna (Low) when 21.5 is enough.
| Metric | GPT-6.1 Sol (High) | GPT-6 Luna (Low) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 50.2 | 21.5 | −57.2% GPT-6 Luna (Low) is 57.2% less intelligent |
| Total AA cost (lower is better) | $521.32 | $10.63 | −98.0% GPT-6 Luna (Low) is 98.0% cheaper |
| End-to-end time (lower is better) | 82.55s | 7.26s | −91.2% GPT-6 Luna (Low) is 91.2% faster |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
GPT-6 Luna (Low) vs GPT-6.1 Sol (High): 57.2% less intelligence, 98.0% less cost to run the AA benchmark, and 91.2% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6.1 Sol (High) is on today's frontier: nothing is both smarter and cheaper.
- GPT-6 Luna (Low) is on today's frontier: nothing is both smarter and cheaper.
GPT-6.1 Sol (High)GPT-6 Luna (Low)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-6-1-sol-high/gpt-6-luna-low · Markdown: /api/v1/compare/gpt-6-1-sol-high/gpt-6-luna-low?format=md · llms.txt · agent skill