Granite 4.2 30B vs Inkling Small
Which is better for the money: Granite 4.2 30B by IBM or Inkling Small by Thinking Machines? 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
Inkling Small scores 13.0 points higher (25.7 vs 12.7) but costs 2.2× as much to run the benchmark ($241 vs $111; both mid-range class). Pick Inkling Small when the extra intelligence is worth the premium, otherwise Granite 4.2 30B.
| Metric | Granite 4.2 30B | Inkling Small | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 12.7 | 25.7 | +102.4% Inkling Small is 2.0× more intelligent |
| Total AA cost (lower is better) | $110.83 | $240.85 | +117.3% Inkling Small is 2.2× more expensive |
| End-to-end time (lower is better) | 51.51s | 12.80s | −75.2% Inkling Small is 75.2% faster |
| Price per 1M tokens (in / out) | $0.16 / $0.65 | $0.30 / $1.20 | |
| Input modalities | Text | Text, Image, Speech |
Inkling Small vs Granite 4.2 30B: 102.4% more intelligence, 117.3% more cost to run the AA benchmark, and 75.2% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Granite 4.2 30B is off the frontier: at the same or lower cost, MiMo-V2.6-Flash scores 37.90 for $110.
- Inkling Small is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
Granite 4.2 30BInkling 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/granite-4-2-30b/inkling-small · Markdown: /api/v1/compare/granite-4-2-30b/inkling-small?format=md · llms.txt · agent skill