Mistral Large 4 (Medium) vs Mistral Small 4 (Reasoning)
Which is better for the money: Mistral Large 4 (Medium) by Mistral or Mistral Small 4 (Reasoning) by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-29.
Trade-off
Verdict
Depends on your budget
Mistral Large 4 (Medium) scores 18.8 points higher (23.1 vs 4.3) but costs 22× as much to run the benchmark ($936 vs $43.4; premium vs budget cost classes). They are not alternatives at one budget: pick Mistral Large 4 (Medium) when you need intelligence above 4.3, and Mistral Small 4 (Reasoning) when 4.3 is enough.
| Metric | Mistral Large 4 (Medium) | Mistral Small 4 (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 23.1 | 4.3 | −81.4% Mistral Small 4 (Reas… is 81.4% less intelligent |
| Total AA cost (lower is better) | $936.36 | $43.43 | −95.4% Mistral Small 4 (Reas… is 95.4% cheaper |
| End-to-end time (lower is better) | Not reported | 15.01s | — not comparable |
| Price per 1M tokens (in / out) | $0.70 / $2.10 | $0.15 / $0.60 | |
| Input modalities | Text, Image | Text, Image |
Mistral Small 4 (Reasoning) vs Mistral Large 4 (Medium): 81.4% less intelligence, 95.4% less cost to run the AA benchmark, and end-to-end time not fully reported.
Today's Pareto frontier
Against the frontier
- Mistral Large 4 (Medium) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 52.30 for $718.
- Mistral Small 4 (Reasoning) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Low) scores 18.60 for $39.6.
Mistral Large 4 (Medium)Mistral 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-large-4-medium/mistral-small-4 · Markdown: /api/v1/compare/mistral-large-4-medium/mistral-small-4?format=md · llms.txt · agent skill