Gemini 3.1 Pro Preview vs MiniMax-M3
Which is better for the money: Gemini 3.1 Pro Preview by Google 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
Gemini 3.1 Pro Preview scores 0.5 points higher (29.7 vs 29.2) but costs 3.6× as much to run the benchmark ($1935 vs $538; both premium class). They are not alternatives at one budget: pick Gemini 3.1 Pro Preview when you need intelligence above 29.2, and MiniMax-M3 when 29.2 is enough.
| Metric | Gemini 3.1 Pro Preview | MiniMax-M3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 29.7 | 29.2 | −1.7% MiniMax-M3 is 1.7% less intelligent |
| Total AA cost (lower is better) | $1,935.39 | $537.98 | −72.2% MiniMax-M3 is 72.2% cheaper |
| End-to-end time (lower is better) | 24.90s | 26.74s | +7.4% MiniMax-M3 is 7.4% slower |
| Price per 1M tokens (in / out) | $2.00 / $12.0 | $0.30 / $1.20 | |
| Input modalities | Text, Image, Speech, Video | Text, Image, Video |
MiniMax-M3 vs Gemini 3.1 Pro Preview: 1.7% less intelligence, 72.2% less cost to run the AA benchmark, and 7.4% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Gemini 3.1 Pro Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- MiniMax-M3 is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
Gemini 3.1 Pro PreviewMiniMax-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/gemini-3-1-pro-preview/minimax-m3 · Markdown: /api/v1/compare/gemini-3-1-pro-preview/minimax-m3?format=md · llms.txt · agent skill