Mercury 2 vs Ministral 3 14B
Which is better for the money: Mercury 2 by Inception or Ministral 3 14B by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
Mercury 2 scores 4.8 points higher (10.8 vs 6.0) but costs 2.8× as much to run the benchmark ($105 vs $37.6; mid-range vs budget cost classes). Pick Mercury 2 when the extra intelligence is worth the premium, otherwise Ministral 3 14B.
| Metric | Mercury 2 | Ministral 3 14B | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 10.8 | 6.0 | −44.4% Ministral 3 14B is 44.4% less intelligent |
| Total AA cost (lower is better) | $104.94 | $37.56 | −64.2% Ministral 3 14B is 64.2% cheaper |
| End-to-end time (lower is better) | 6.54s | 8.02s | +22.6% Ministral 3 14B is 22.6% slower |
| Price per 1M tokens (in / out) | $0.25 / $0.75 | $0.20 / $0.20 | |
| Input modalities | Text | Text, Image |
Ministral 3 14B vs Mercury 2: 44.4% less intelligence, 64.2% less cost to run the AA benchmark, and 22.6% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Mercury 2 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
- Ministral 3 14B is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
Mercury 2Ministral 3 14BToday'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/mercury-2/ministral-3-14b · Markdown: /api/v1/compare/mercury-2/ministral-3-14b?format=md · llms.txt · agent skill