Gemini 4 Carbon (High) vs Inkling Small
Which is better for the money: Gemini 4 Carbon (High) by Google or Inkling Small by Thinking Machines? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-29.
Trade-off
Verdict
Depends on your budget
Gemini 4 Carbon (High) scores 46.5 points higher (59.4 vs 12.9) but costs 37× as much to run the benchmark ($8240 vs $225; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Gemini 4 Carbon (High) when you need intelligence above 12.9, and Inkling Small when 12.9 is enough.
| Metric | Gemini 4 Carbon (High) | Inkling Small | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 59.4 | 12.9 | −78.3% Inkling Small is 78.3% less intelligent |
| Total AA cost (lower is better) | $8,239.69 | $224.77 | −97.3% Inkling Small is 97.3% cheaper |
| End-to-end time (lower is better) | 105.19s | 13.64s | −87.0% Inkling Small is 87.0% faster |
| Price per 1M tokens (in / out) | $4.00 / $20.0 | $0.30 / $1.20 | |
| Input modalities | Text, Image, Speech, Video | Text, Image, Speech |
Inkling Small vs Gemini 4 Carbon (High): 78.3% less intelligence, 97.3% less cost to run the AA benchmark, and 87.0% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Gemini 4 Carbon (High) is on today's frontier: nothing is both smarter and cheaper.
- Inkling Small is off the frontier: at the same or lower cost, GPT-6.1 Terra (Medium) scores 38.10 for $190.
Gemini 4 Carbon (High)Inkling 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/gemini-4-carbon/inkling-small · Markdown: /api/v1/compare/gemini-4-carbon/inkling-small?format=md · llms.txt · agent skill