GPT-6 Luna (Max) vs GPT-6 Sol (Low)
Which is better for the money: GPT-6 Luna (Max) by OpenAI or GPT-6 Sol (Low) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Clear winner
Verdict
Pick GPT-6 Luna (Max)
GPT-6 Sol (Low) vs GPT-6 Luna (Max): 10.2% less intelligence, 120.2% more cost to run the AA benchmark, and 92.3% faster end-to-end.
| Metric | GPT-6 Luna (Max) | GPT-6 Sol (Low) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 38.1 | 34.2 | −10.2% GPT-6 Sol (Low) is 10.2% less intelligent |
| Total AA cost (lower is better) | $122.05 | $268.73 | +120.2% GPT-6 Sol (Low) is 2.2× more expensive |
| End-to-end time (lower is better) | 82.02s | 6.34s | −92.3% GPT-6 Sol (Low) is 92.3% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $2.00 / $10.0 | |
| Input modalities | Text, Image | Text, Image |
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (Max) is on today's frontier: nothing is both smarter and cheaper.
- GPT-6 Sol (Low) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
GPT-6 Luna (Max)GPT-6 Sol (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-luna/gpt-6-sol-low · Markdown: /api/v1/compare/gpt-6-luna/gpt-6-sol-low?format=md · llms.txt · agent skill