GPT-6 Luna (Low) vs MiniMax-M3
Which is better for the money: GPT-6 Luna (Low) by OpenAI or MiniMax-M3 by MiniMax? 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
MiniMax-M3 scores 7.7 points higher (29.2 vs 21.5) but costs 51× as much to run the benchmark ($538 vs $10.6; premium vs budget cost classes). They are not alternatives at one budget: pick MiniMax-M3 when you need intelligence above 21.5, and GPT-6 Luna (Low) when 21.5 is enough.
| Metric | GPT-6 Luna (Low) | MiniMax-M3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 21.5 | 29.2 | +35.8% MiniMax-M3 is 35.8% more intelligent |
| Total AA cost (lower is better) | $10.63 | $537.98 | +4961.0% MiniMax-M3 is 51× more expensive |
| End-to-end time (lower is better) | 6.60s | 26.74s | +305.2% MiniMax-M3 is 305.2% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.30 / $1.20 | |
| Input modalities | Text, Image | Text, Image, Video |
MiniMax-M3 vs GPT-6 Luna (Low): 35.8% more intelligence, 4961.0% more cost to run the AA benchmark, and 305.2% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (Low) is on today's frontier: nothing is both smarter and cheaper.
- MiniMax-M3 is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
GPT-6 Luna (Low)MiniMax-M3Today's Pareto frontierOpen-weights 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-low/minimax-m3 · Markdown: /api/v1/compare/gpt-6-luna-low/minimax-m3?format=md · llms.txt · agent skill