GPT-6.1 Sol (Low) vs GPT-6 Luna (High)
Which is better for the money: GPT-6.1 Sol (Low) by OpenAI or GPT-6 Luna (High) 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 (Low) scores 9.2 points higher (42.1 vs 32.9) but costs 5.2× as much to run the benchmark ($250 vs $47.9; mid-range vs budget cost classes). They are not alternatives at one budget: pick GPT-6.1 Sol (Low) when you need intelligence above 32.9, and GPT-6 Luna (High) when 32.9 is enough.
| Metric | GPT-6.1 Sol (Low) | GPT-6 Luna (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 42.1 | 32.9 | −21.9% GPT-6 Luna (High) is 21.9% less intelligent |
| Total AA cost (lower is better) | $250.48 | $47.85 | −80.9% GPT-6 Luna (High) is 80.9% cheaper |
| End-to-end time (lower is better) | 12.91s | 21.44s | +66.1% GPT-6 Luna (High) is 66.1% slower |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
GPT-6 Luna (High) vs GPT-6.1 Sol (Low): 21.9% less intelligence, 80.9% less cost to run the AA benchmark, and 66.1% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6.1 Sol (Low) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- GPT-6 Luna (High) is on today's frontier: nothing is both smarter and cheaper.
GPT-6.1 Sol (Low)GPT-6 Luna (High)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-low/gpt-6-luna-high · Markdown: /api/v1/compare/gpt-6-1-sol-low/gpt-6-luna-high?format=md · llms.txt · agent skill