MiMo-V2.5-Pro (Reasoning) vs Qwen3.8 Max (0902)
Which is better for the money: MiMo-V2.5-Pro (Reasoning) by Xiaomi or Qwen3.8 Max (0902) by Alibaba? 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
Qwen3.8 Max (0902) scores 19.4 points higher (45.4 vs 26.0) but costs 21× as much to run the benchmark ($4935 vs $231; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Qwen3.8 Max (0902) when you need intelligence above 26.0, and MiMo-V2.5-Pro (Reasoning) when 26.0 is enough.
| Metric | MiMo-V2.5-Pro (Reasoning) | Qwen3.8 Max (0902) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 26.0 | 45.4 | +74.6% Qwen3.8 Max (0902) is 74.6% more intelligent |
| Total AA cost (lower is better) | $231.08 | $4,934.79 | +2035.5% Qwen3.8 Max (0902) is 21× more expensive |
| End-to-end time (lower is better) | 49.58s | 64.05s | +29.2% Qwen3.8 Max (0902) is 29.2% slower |
| Price per 1M tokens (in / out) | $0.41 / $1.02 | $2.00 / $6.00 | |
| Input modalities | Text | Text, Image |
Qwen3.8 Max (0902) vs MiMo-V2.5-Pro (Reasoning): 74.6% more intelligence, 2035.5% more cost to run the AA benchmark, and 29.2% slower end-to-end.
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 Max (0902) is off the frontier: at the same or lower cost, Claude Opus 5.5 (Xhigh, Default Fallback) scores 56.00 for $4057.
MiMo-V2.5-Pro (Reasoning)Qwen3.8 Max (0902)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-max · Markdown: /api/v1/compare/mimo-v2-5-pro/qwen3-8-max?format=md · llms.txt · agent skill