MiniMax-M3 vs Mistral Large 3
Which is better for the money: MiniMax-M3 by MiniMax or Mistral Large 3 by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
MiniMax-M3 scores 19.9 points higher (29.2 vs 9.3) but costs 12× as much to run the benchmark ($538 vs $46.4; premium vs budget cost classes). They are not alternatives at one budget: pick MiniMax-M3 when you need intelligence above 9.3, and Mistral Large 3 when 9.3 is enough.
| Metric | MiniMax-M3 | Mistral Large 3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 29.2 | 9.3 | −68.2% Mistral Large 3 is 68.2% less intelligent |
| Total AA cost (lower is better) | $537.98 | $46.41 | −91.4% Mistral Large 3 is 91.4% cheaper |
| End-to-end time (lower is better) | 25.25s | 7.23s | −71.4% Mistral Large 3 is 71.4% faster |
| Price per 1M tokens (in / out) | $0.30 / $1.20 | $0.50 / $1.50 | |
| Input modalities | Text, Image, Video | Text, Image |
Mistral Large 3 vs MiniMax-M3: 68.2% less intelligence, 91.4% less cost to run the AA benchmark, and 71.4% faster end-to-end.
Today's Pareto frontier
Against the frontier
- MiniMax-M3 is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
- Mistral Large 3 is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
MiniMax-M3Mistral Large 3Today'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/minimax-m3/mistral-large-3 · Markdown: /api/v1/compare/minimax-m3/mistral-large-3?format=md · llms.txt · agent skill