MiMo-V2.5 vs Qwen3.5 397B A17B (Reasoning)
Which is better for the money: MiMo-V2.5 by Xiaomi or Qwen3.5 397B A17B (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
Qwen3.5 397B A17B (Reasoning) vs MiMo-V2.5: 15.6% less intelligence, 1419.4% more cost to run the AA benchmark, and 2.5% faster end-to-end.
| Metric | MiMo-V2.5 | Qwen3.5 397B A17B (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 21.8 | 18.4 | −15.6% Qwen3.5 397B A17B (Re… is 15.6% less intelligent |
| Total AA cost (lower is better) | $61.93 | $940.97 | +1419.4% Qwen3.5 397B A17B (Re… is 15× more expensive |
| End-to-end time (lower is better) | 66.80s | 65.10s | −2.5% Qwen3.5 397B A17B (Re… is 2.5% faster |
| Price per 1M tokens (in / out) | $0.13 / $0.27 | $0.60 / $3.60 | |
| Input modalities | Text, Image | Text, Image |
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.
- Qwen3.5 397B A17B (Reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 51.00 for $662.
MiMo-V2.5Qwen3.5 397B A17B (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/qwen3-5-397b-a17b · Markdown: /api/v1/compare/mimo-v2-5-0424/qwen3-5-397b-a17b?format=md · llms.txt · agent skill