Mistral Medium 3.5 vs Mistral Small 3.1
Which is better for the money: Mistral Medium 3.5 by Mistral or Mistral Small 3.1 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
Mistral Medium 3.5 scores 7.1 points higher (14.2 vs 7.1) but costs 45× as much to run the benchmark ($1264 vs $27.8; premium vs budget cost classes). They are not alternatives at one budget: pick Mistral Medium 3.5 when you need intelligence above 7.1, and Mistral Small 3.1 when 7.1 is enough.
| Metric | Mistral Medium 3.5 | Mistral Small 3.1 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 14.2 | 7.1 | −50.0% Mistral Small 3.1 is 50.0% less intelligent |
| Total AA cost (lower is better) | $1,263.80 | $27.82 | −97.8% Mistral Small 3.1 is 97.8% cheaper |
| End-to-end time (lower is better) | 17.77s | 11.78s | −33.7% Mistral Small 3.1 is 33.7% faster |
| Price per 1M tokens (in / out) | $1.50 / $7.50 | $0.08 / $0.14 | |
| Input modalities | Text, Image | Text, Image |
Mistral Small 3.1 vs Mistral Medium 3.5: 50.0% less intelligence, 97.8% less cost to run the AA benchmark, and 33.7% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Mistral Medium 3.5 is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- Mistral Small 3.1 is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
Mistral Medium 3.5Mistral Small 3.1Today'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/mistral-medium-3-5/mistral-small-3-1 · Markdown: /api/v1/compare/mistral-medium-3-5/mistral-small-3-1?format=md · llms.txt · agent skill