MiniMax-M3.1-Flash vs Mistral Small 4 (Reasoning)
Which is better for the money: MiniMax-M3.1-Flash by MiniMax or Mistral Small 4 (Reasoning) by Mistral? 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-M3.1-Flash scores 31.4 points higher (42.7 vs 11.3) but costs 6.7× as much to run the benchmark ($283 vs $42.5; mid-range vs budget cost classes). They are not alternatives at one budget: pick MiniMax-M3.1-Flash when you need intelligence above 11.3, and Mistral Small 4 (Reasoning) when 11.3 is enough.
| Metric | MiniMax-M3.1-Flash | Mistral Small 4 (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 42.7 | 11.3 | −73.5% Mistral Small 4 (Reas… is 73.5% less intelligent |
| Total AA cost (lower is better) | $283.18 | $42.50 | −85.0% Mistral Small 4 (Reas… is 85.0% cheaper |
| End-to-end time (lower is better) | 25.34s | 14.50s | −42.8% Mistral Small 4 (Reas… is 42.8% faster |
| Price per 1M tokens (in / out) | $0.15 / $0.60 | $0.15 / $0.60 | |
| Input modalities | Text, Image | Text, Image |
Mistral Small 4 (Reasoning) vs MiniMax-M3.1-Flash: 73.5% less intelligence, 85.0% less cost to run the AA benchmark, and 42.8% faster end-to-end.
Today's Pareto frontier
Against the frontier
- MiniMax-M3.1-Flash is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- Mistral Small 4 (Reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
MiniMax-M3.1-FlashMistral Small 4 (Reasoning)Today'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-m3-1-flash/mistral-small-4 · Markdown: /api/v1/compare/minimax-m3-1-flash/mistral-small-4?format=md · llms.txt · agent skill