MiMo-V2.5 vs Ministral 3 8B
Which is better for the money: MiMo-V2.5 by Xiaomi or Ministral 3 8B 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
MiMo-V2.5 scores 16.3 points higher (21.8 vs 5.5) but costs 2.3× as much to run the benchmark ($61.9 vs $27.5; mid-range vs budget cost classes). Pick MiMo-V2.5 when the extra intelligence is worth the premium, otherwise Ministral 3 8B.
| Metric | MiMo-V2.5 | Ministral 3 8B | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 21.8 | 5.5 | −74.8% Ministral 3 8B is 74.8% less intelligent |
| Total AA cost (lower is better) | $61.93 | $27.47 | −55.6% Ministral 3 8B is 55.6% cheaper |
| End-to-end time (lower is better) | 66.80s | 5.26s | −92.1% Ministral 3 8B is 92.1% faster |
| Price per 1M tokens (in / out) | $0.13 / $0.27 | $0.15 / $0.15 | |
| Input modalities | Text, Image | Text, Image |
Ministral 3 8B vs MiMo-V2.5: 74.8% less intelligence, 55.6% less cost to run the AA benchmark, and 92.1% faster end-to-end.
Today's Pareto frontier
Against the frontier
- MiMo-V2.5 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Medium) scores 34.50 for $56.4.
- Ministral 3 8B is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
MiMo-V2.5Ministral 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/mimo-v2-5-0424/ministral-3-8b · Markdown: /api/v1/compare/mimo-v2-5-0424/ministral-3-8b?format=md · llms.txt · agent skill