Qwen3.5 122B A10B (Reasoning) vs Qwen3.8 Max (0902)
Which is better for the money: Qwen3.5 122B A10B (Reasoning) by Alibaba or Qwen3.8 Max (0902) by Alibaba? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.
Trade-off
Verdict
Depends on your budget
Qwen3.8 Max (0902) scores 29.8 points higher (45.4 vs 15.6) but costs 7.5× as much to run the benchmark ($4935 vs $661; flagship vs premium cost classes). They are not alternatives at one budget: pick Qwen3.8 Max (0902) when you need intelligence above 15.6, and Qwen3.5 122B A10B (Reasoning) when 15.6 is enough.
| Metric | Qwen3.5 122B A10B (Reasoning) | Qwen3.8 Max (0902) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 15.6 | 45.4 | +191.0% Qwen3.8 Max (0902) is 2.9× more intelligent |
| Total AA cost (lower is better) | $661.29 | $4,934.79 | +646.2% Qwen3.8 Max (0902) is 7.5× more expensive |
| End-to-end time (lower is better) | 21.22s | 63.77s | +200.5% Qwen3.8 Max (0902) is 200.5% slower |
| Price per 1M tokens (in / out) | $0.40 / $3.20 | $2.00 / $6.00 | |
| Input modalities | Text, Image | Text, Image |
Qwen3.8 Max (0902) vs Qwen3.5 122B A10B (Reasoning): 191.0% more intelligence, 646.2% more cost to run the AA benchmark, and 200.5% slower 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.
- Qwen3.8 Max (0902) is off the frontier: at the same or lower cost, Claude Opus 5.5 (Xhigh, Default Fallback) scores 56.00 for $4057.
Qwen3.5 122B A10B (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/qwen3-5-122b-a10b/qwen3-8-max · Markdown: /api/v1/compare/qwen3-5-122b-a10b/qwen3-8-max?format=md · llms.txt · agent skill