MiMo-V2.5 vs Mistral Small 4 (Reasoning)
Which is better for the money: MiMo-V2.5 by Xiaomi or Mistral Small 4 (Reasoning) 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
MiMo-V2.5 scores 10.5 points higher (21.8 vs 11.3) but costs 1.5× as much to run the benchmark ($61.9 vs $42.5; mid-range vs budget cost classes). Pick MiMo-V2.5 when the extra intelligence is worth the premium, otherwise Mistral Small 4 (Reasoning).
| Metric | MiMo-V2.5 | Mistral Small 4 (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 21.8 | 11.3 | −48.2% Mistral Small 4 (Reas… is 48.2% less intelligent |
| Total AA cost (lower is better) | $61.93 | $42.50 | −31.4% Mistral Small 4 (Reas… is 31.4% cheaper |
| End-to-end time (lower is better) | 46.61s | 14.77s | −68.3% Mistral Small 4 (Reas… is 68.3% faster |
| Price per 1M tokens (in / out) | $0.13 / $0.27 | $0.15 / $0.60 | |
| Input modalities | Text, Image | Text, Image |
Mistral Small 4 (Reasoning) vs MiMo-V2.5: 48.2% less intelligence, 31.4% less cost to run the AA benchmark, and 68.3% 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.
- Mistral Small 4 (Reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
MiMo-V2.5Mistral Small 4 (Reasoning)Today'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/mistral-small-4 · Markdown: /api/v1/compare/mimo-v2-5-0424/mistral-small-4?format=md · llms.txt · agent skill