Mistral Medium 3.5 vs Mistral Small 4 (Reasoning)
Which is better for the money: Mistral Medium 3.5 by Mistral or Mistral Small 4 (Reasoning) 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 2.9 points higher (14.2 vs 11.3) but costs 30× as much to run the benchmark ($1264 vs $42.5; premium vs budget cost classes). They are not alternatives at one budget: pick Mistral Medium 3.5 when you need intelligence above 11.3, and Mistral Small 4 (Reasoning) when 11.3 is enough.
| Metric | Mistral Medium 3.5 | Mistral Small 4 (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 14.2 | 11.3 | −20.4% Mistral Small 4 (Reas… is 20.4% less intelligent |
| Total AA cost (lower is better) | $1,263.80 | $42.50 | −96.6% Mistral Small 4 (Reas… is 96.6% cheaper |
| End-to-end time (lower is better) | 17.66s | 14.45s | −18.2% Mistral Small 4 (Reas… is 18.2% faster |
| Price per 1M tokens (in / out) | $1.50 / $7.50 | $0.15 / $0.60 | |
| Input modalities | Text, Image | Text, Image |
Mistral Small 4 (Reasoning) vs Mistral Medium 3.5: 20.4% less intelligence, 96.6% less cost to run the AA benchmark, and 18.2% 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 4 (Reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
Mistral Medium 3.5Mistral 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/mistral-medium-3-5/mistral-small-4 · Markdown: /api/v1/compare/mistral-medium-3-5/mistral-small-4?format=md · llms.txt · agent skill