Ministral 3 14B vs Ministral 3 8B
Which is better for the money: Ministral 3 14B by Mistral or Ministral 3 8B 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 0.5 points higher (6.0 vs 5.5) but costs 1.4× as much to run the benchmark ($37.6 vs $27.5; both budget class). Pick Ministral 3 14B when the extra intelligence is worth the premium, otherwise Ministral 3 8B.
| Metric | Ministral 3 14B | Ministral 3 8B | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.0 | 5.5 | −8.3% Ministral 3 8B is 8.3% less intelligent |
| Total AA cost (lower is better) | $37.56 | $27.47 | −26.9% Ministral 3 8B is 26.9% cheaper |
| End-to-end time (lower is better) | 7.57s | 5.75s | −24.0% Ministral 3 8B is 24.0% faster |
| Price per 1M tokens (in / out) | $0.20 / $0.20 | $0.15 / $0.15 | |
| Input modalities | Text, Image | Text, Image |
Ministral 3 8B vs Ministral 3 14B: 8.3% less intelligence, 26.9% less cost to run the AA benchmark, and 24.0% 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 8B is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
Ministral 3 14BMinistral 3 8BToday'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-3-8b · Markdown: /api/v1/compare/ministral-3-14b/ministral-3-8b?format=md · llms.txt · agent skill