Mistral Large 4 Preview vs Mistral Medium 3.5
Which is better for the money: Mistral Large 4 Preview by Mistral or Mistral Medium 3.5 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 Large 4 Preview scores 24.2 points higher (38.4 vs 14.2) but costs 1.3× as much to run the benchmark ($1608 vs $1264; both premium class). Pick Mistral Large 4 Preview when the extra intelligence is worth the premium, otherwise Mistral Medium 3.5.
| Metric | Mistral Large 4 Preview | Mistral Medium 3.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 38.4 | 14.2 | −63.0% Mistral Medium 3.5 is 63.0% less intelligent |
| Total AA cost (lower is better) | $1,607.86 | $1,263.80 | −21.4% Mistral Medium 3.5 is 21.4% cheaper |
| End-to-end time (lower is better) | 25.73s | 17.66s | −31.4% Mistral Medium 3.5 is 31.4% faster |
| Price per 1M tokens (in / out) | $1.36 / $4.18 | $1.50 / $7.50 | |
| Input modalities | Text, Image | Text, Image |
Mistral Medium 3.5 vs Mistral Large 4 Preview: 63.0% less intelligence, 21.4% less cost to run the AA benchmark, and 31.4% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Mistral Large 4 Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- 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 Large 4 PreviewMistral Medium 3.5Today'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/mistral-medium-3-5 · Markdown: /api/v1/compare/mistral-large-4/mistral-medium-3-5?format=md · llms.txt · agent skill