GPT-6 Luna (High) vs MiniMax-M3
Which is better for the money: GPT-6 Luna (High) by OpenAI or MiniMax-M3 by MiniMax? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Clear winner
Verdict
Pick GPT-6 Luna (High)
MiniMax-M3 vs GPT-6 Luna (High): 11.2% less intelligence, 1024.3% more cost to run the AA benchmark, and 66.0% slower end-to-end.
| Metric | GPT-6 Luna (High) | MiniMax-M3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 32.9 | 29.2 | −11.2% MiniMax-M3 is 11.2% less intelligent |
| Total AA cost (lower is better) | $47.85 | $537.98 | +1024.3% MiniMax-M3 is 11× more expensive |
| End-to-end time (lower is better) | 14.65s | 24.32s | +66.0% MiniMax-M3 is 66.0% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.30 / $1.20 | |
| Input modalities | Text, Image | Text, Image, Video |
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (High) 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 (High)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-high/minimax-m3 · Markdown: /api/v1/compare/gpt-6-luna-high/minimax-m3?format=md · llms.txt · agent skill