MiniMax-M2.7 vs Qwen3.5 122B A10B (Reasoning)
Which is better for the money: MiniMax-M2.7 by MiniMax or Qwen3.5 122B A10B (Reasoning) by Alibaba? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.
Clear winner
Verdict
Pick MiniMax-M2.7
Qwen3.5 122B A10B (Reasoning) vs MiniMax-M2.7: 31.6% less intelligence, 171.7% more cost to run the AA benchmark, and 60.6% faster end-to-end.
| Metric | MiniMax-M2.7 | Qwen3.5 122B A10B (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 22.8 | 15.6 | −31.6% Qwen3.5 122B A10B (Re… is 31.6% less intelligent |
| Total AA cost (lower is better) | $243.38 | $661.29 | +171.7% Qwen3.5 122B A10B (Re… is 2.7× more expensive |
| End-to-end time (lower is better) | 53.88s | 21.24s | −60.6% Qwen3.5 122B A10B (Re… is 60.6% faster |
| Price per 1M tokens (in / out) | $0.30 / $1.20 | $0.40 / $3.20 | |
| Input modalities | Text | Text, Image |
Today's Pareto frontier
Against the frontier
- MiniMax-M2.7 is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- Qwen3.5 122B A10B (Reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
MiniMax-M2.7Qwen3.5 122B A10B (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/minimax-m2-7/qwen3-5-122b-a10b · Markdown: /api/v1/compare/minimax-m2-7/qwen3-5-122b-a10b?format=md · llms.txt · agent skill