MiMo-V2.5-Pro (Reasoning) vs Qwen3.8 27B (Non-reasoning)
Which is better for the money: MiMo-V2.5-Pro (Reasoning) by Xiaomi or Qwen3.8 27B (Non-reasoning) by Alibaba? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Clear winner
Verdict
Pick MiMo-V2.5-Pro (Reasoning)
Qwen3.8 27B (Non-reasoning) vs MiMo-V2.5-Pro (Reasoning): 22.3% less intelligence, 775.2% more cost to run the AA benchmark, and 71.8% faster end-to-end.
| Metric | MiMo-V2.5-Pro (Reasoning) | Qwen3.8 27B (Non-reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 26.0 | 20.2 | −22.3% Qwen3.8 27B (Non-reas… is 22.3% less intelligent |
| Total AA cost (lower is better) | $231.08 | $2,022.49 | +775.2% Qwen3.8 27B (Non-reas… is 8.8× more expensive |
| End-to-end time (lower is better) | 49.50s | 13.95s | −71.8% Qwen3.8 27B (Non-reas… is 71.8% faster |
| Price per 1M tokens (in / out) | $0.41 / $1.02 | $0.50 / $3.00 | |
| Input modalities | Text | Text, Image, Video |
Today's Pareto frontier
Against the frontier
- MiMo-V2.5-Pro (Reasoning) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- Qwen3.8 27B (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
MiMo-V2.5-Pro (Reasoning)Qwen3.8 27B (Non-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-pro/qwen3-8-27b-non-reasoning · Markdown: /api/v1/compare/mimo-v2-5-pro/qwen3-8-27b-non-reasoning?format=md · llms.txt · agent skill