Inkling Small vs Qwen3.8 Max (0902)
Which is better for the money: Inkling Small by Thinking Machines or Qwen3.8 Max (0902) by Alibaba? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
Qwen3.8 Max (0902) scores 19.7 points higher (45.4 vs 25.7) but costs 20× as much to run the benchmark ($4935 vs $241; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Qwen3.8 Max (0902) when you need intelligence above 25.7, and Inkling Small when 25.7 is enough.
| Metric | Inkling Small | Qwen3.8 Max (0902) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 25.7 | 45.4 | +76.7% Qwen3.8 Max (0902) is 76.7% more intelligent |
| Total AA cost (lower is better) | $240.85 | $4,934.79 | +1948.9% Qwen3.8 Max (0902) is 20× more expensive |
| End-to-end time (lower is better) | 12.68s | 64.05s | +405.1% Qwen3.8 Max (0902) is 405.1% slower |
| Price per 1M tokens (in / out) | $0.30 / $1.20 | $2.00 / $6.00 | |
| Input modalities | Text, Image, Speech | Text, Image |
Qwen3.8 Max (0902) vs Inkling Small: 76.7% more intelligence, 1948.9% more cost to run the AA benchmark, and 405.1% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Inkling Small is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- 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.
Inkling SmallQwen3.8 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/inkling-small/qwen3-8-max · Markdown: /api/v1/compare/inkling-small/qwen3-8-max?format=md · llms.txt · agent skill