Ministral 3 14B vs Ministral 3 3B
Which is better for the money: Ministral 3 14B by Mistral or Ministral 3 3B by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.
Trade-off
Verdict
Depends on your budget
Ministral 3 14B scores 1.2 points higher (6.0 vs 4.8) but costs 3.1× as much to run the benchmark ($37.6 vs $12.2; both budget class). They are not alternatives at one budget: pick Ministral 3 14B when you need intelligence above 4.8, and Ministral 3 3B when 4.8 is enough.
| Metric | Ministral 3 14B | Ministral 3 3B | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.0 | 4.8 | −20.0% Ministral 3 3B is 20.0% less intelligent |
| Total AA cost (lower is better) | $37.56 | $12.23 | −67.4% Ministral 3 3B is 67.4% cheaper |
| End-to-end time (lower is better) | 7.88s | 3.32s | −57.9% Ministral 3 3B is 57.9% faster |
| Price per 1M tokens (in / out) | $0.20 / $0.20 | $0.10 / $0.10 | |
| Input modalities | Text, Image | Text, Image |
Ministral 3 3B vs Ministral 3 14B: 20.0% less intelligence, 67.4% less cost to run the AA benchmark, and 57.9% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Ministral 3 14B is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
- Ministral 3 3B is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
Ministral 3 14BMinistral 3 3BToday'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/ministral-3-14b/ministral-3-3b · Markdown: /api/v1/compare/ministral-3-14b/ministral-3-3b?format=md · llms.txt · agent skill