Inkling Small vs Qwen3.6 35B A3B (Reasoning)
Which is better for the money: Inkling Small by Thinking Machines or Qwen3.6 35B A3B (Reasoning) by Alibaba? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick Inkling Small
Qwen3.6 35B A3B (Reasoning) vs Inkling Small: 29.2% less intelligence, 272.2% more cost to run the AA benchmark, and 266.6% slower end-to-end.
| Metric | Inkling Small | Qwen3.6 35B A3B (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 25.7 | 18.2 | −29.2% Qwen3.6 35B A3B (Reas… is 29.2% less intelligent |
| Total AA cost (lower is better) | $240.85 | $896.39 | +272.2% Qwen3.6 35B A3B (Reas… is 3.7× more expensive |
| End-to-end time (lower is better) | 12.95s | 47.48s | +266.6% Qwen3.6 35B A3B (Reas… is 266.6% slower |
| Price per 1M tokens (in / out) | $0.30 / $1.20 | $0.38 / $2.25 | |
| Input modalities | Text, Image, Speech | Text, Image, Video |
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.
- Qwen3.6 35B A3B (Reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 51.00 for $662.
Inkling SmallQwen3.6 35B A3B (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/inkling-small/qwen3-6-35b-a3b · Markdown: /api/v1/compare/inkling-small/qwen3-6-35b-a3b?format=md · llms.txt · agent skill