Hy3 vs Inkling Small
Which is better for the money: Hy3 by Tencent or Inkling Small by Thinking Machines? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
Inkling Small scores 0.4 points higher (25.7 vs 25.3) but costs 1.6× as much to run the benchmark ($241 vs $150; both mid-range class). Pick Inkling Small when the extra intelligence is worth the premium, otherwise Hy3.
| Metric | Hy3 | Inkling Small | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 25.3 | 25.7 | +1.6% Inkling Small is 1.6% more intelligent |
| Total AA cost (lower is better) | $149.61 | $240.85 | +61.0% Inkling Small is 61.0% more expensive |
| End-to-end time (lower is better) | 33.29s | 12.67s | −61.9% Inkling Small is 61.9% faster |
| Price per 1M tokens (in / out) | $0.14 / $0.56 | $0.30 / $1.20 | |
| Input modalities | Text | Text, Image, Speech |
Inkling Small vs Hy3: 1.6% more intelligence, 61.0% more cost to run the AA benchmark, and 61.9% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Hy3 is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
- Inkling Small is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
Hy3Inkling SmallToday'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/hy3/inkling-small · Markdown: /api/v1/compare/hy3/inkling-small?format=md · llms.txt · agent skill