Qwen3.5 397B A17B (Reasoning) vs Qwen3.8 27B (Non-reasoning)
Which is better for the money: Qwen3.5 397B A17B (Reasoning) by Alibaba or Qwen3.8 27B (Non-reasoning) 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 27B (Non-reasoning) scores 1.8 points higher (20.2 vs 18.4) but costs 2.1× as much to run the benchmark ($2022 vs $941; flagship vs premium cost classes). Pick Qwen3.8 27B (Non-reasoning) when the extra intelligence is worth the premium, otherwise Qwen3.5 397B A17B (Reasoning).
| Metric | Qwen3.5 397B A17B (Reasoning) | Qwen3.8 27B (Non-reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 18.4 | 20.2 | +9.8% Qwen3.8 27B (Non-reas… is 9.8% more intelligent |
| Total AA cost (lower is better) | $940.97 | $2,022.49 | +114.9% Qwen3.8 27B (Non-reas… is 2.1× more expensive |
| End-to-end time (lower is better) | 65.25s | 14.44s | −77.9% Qwen3.8 27B (Non-reas… is 77.9% faster |
| Price per 1M tokens (in / out) | $0.60 / $3.60 | $0.50 / $3.00 | |
| Input modalities | Text, Image | Text, Image, Video |
Qwen3.8 27B (Non-reasoning) vs Qwen3.5 397B A17B (Reasoning): 9.8% more intelligence, 114.9% more cost to run the AA benchmark, and 77.9% faster end-to-end.
Today's Pareto frontier
Against the frontier
- 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.
- Qwen3.8 27B (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Qwen3.5 397B A17B (Reasoning)Qwen3.8 27B (Non-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/qwen3-5-397b-a17b/qwen3-8-27b-non-reasoning · Markdown: /api/v1/compare/qwen3-5-397b-a17b/qwen3-8-27b-non-reasoning?format=md · llms.txt · agent skill