Qwen3.5 122B A10B (Reasoning) vs Qwen3.7 Max
Which is better for the money: Qwen3.5 122B A10B (Reasoning) by Alibaba or Qwen3.7 Max by Alibaba? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
Qwen3.7 Max scores 13.9 points higher (29.5 vs 15.6) but costs 3.0× as much to run the benchmark ($1965 vs $661; both premium class). Pick Qwen3.7 Max when the extra intelligence is worth the premium, otherwise Qwen3.5 122B A10B (Reasoning).
| Metric | Qwen3.5 122B A10B (Reasoning) | Qwen3.7 Max | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 15.6 | 29.5 | +89.1% Qwen3.7 Max is 89.1% more intelligent |
| Total AA cost (lower is better) | $661.29 | $1,964.83 | +197.1% Qwen3.7 Max is 3.0× more expensive |
| End-to-end time (lower is better) | 21.37s | 16.58s | −22.4% Qwen3.7 Max is 22.4% faster |
| Price per 1M tokens (in / out) | $0.40 / $3.20 | $2.50 / $7.50 | |
| Input modalities | Text, Image | Text |
Qwen3.7 Max vs Qwen3.5 122B A10B (Reasoning): 89.1% more intelligence, 197.1% more cost to run the AA benchmark, and 22.4% faster end-to-end.
Today's Pareto frontier
Against the frontier
- 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.
- Qwen3.7 Max is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Qwen3.5 122B A10B (Reasoning)Qwen3.7 MaxToday'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/qwen3-5-122b-a10b/qwen3-7-max · Markdown: /api/v1/compare/qwen3-5-122b-a10b/qwen3-7-max?format=md · llms.txt · agent skill