GPT-5 mini (High) vs MiniMax-M3
Which is better for the money: GPT-5 mini (High) by OpenAI or MiniMax-M3 by MiniMax? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
MiniMax-M3 scores 12.4 points higher (29.2 vs 16.8) but costs 2.9× as much to run the benchmark ($538 vs $189; premium vs mid-range cost classes). Pick MiniMax-M3 when the extra intelligence is worth the premium, otherwise GPT-5 mini (High).
| Metric | GPT-5 mini (High) | MiniMax-M3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 16.8 | 29.2 | +73.8% MiniMax-M3 is 73.8% more intelligent |
| Total AA cost (lower is better) | $188.66 | $537.98 | +185.2% MiniMax-M3 is 2.9× more expensive |
| End-to-end time (lower is better) | 58.72s | 26.74s | −54.5% MiniMax-M3 is 54.5% faster |
| Price per 1M tokens (in / out) | $0.25 / $2.00 | $0.30 / $1.20 | |
| Input modalities | Text, Image | Text, Image, Video |
MiniMax-M3 vs GPT-5 mini (High): 73.8% more intelligence, 185.2% more cost to run the AA benchmark, and 54.5% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-5 mini (High) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
- MiniMax-M3 is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
GPT-5 mini (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-5-mini/minimax-m3 · Markdown: /api/v1/compare/gpt-5-mini/minimax-m3?format=md · llms.txt · agent skill