Gemini 3.7 Flash (high) vs Inkling Small
Which is better for the money: Gemini 3.7 Flash (high) by Google or Inkling Small by Thinking Machines? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-09-09.
Trade-off
Verdict
Depends on your budget
Gemini 3.7 Flash (high) scores 13.3 points higher (39.4 vs 26.1) but costs 4.5× as much to run the benchmark ($1084 vs $241; premium vs mid-range cost classes). They are not alternatives at one budget: pick Gemini 3.7 Flash (high) when you need intelligence above 26.1, and Inkling Small when 26.1 is enough.
| Metric | Gemini 3.7 Flash (high) | Inkling Small | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 39.4 | 26.1 | −33.8% Inkling Small is 33.8% less intelligent |
| Total AA cost (lower is better) | $1,084.46 | $240.85 | −77.8% Inkling Small is 77.8% cheaper |
| End-to-end time (lower is better) | 11.48s | 21.89s | +90.7% Inkling Small is 90.7% slower |
| Price per 1M tokens (in / out) | $0.75 / $3.75 | $0.30 / $1.20 | |
| Input modalities | Not reported | Not reported |
Inkling Small vs Gemini 3.7 Flash (high): 33.8% less intelligence, 77.8% less cost to run the AA benchmark, and 90.7% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Gemini 3.7 Flash (high) is off the frontier: at the same or lower cost, GLM-5.3-Flash scores 41.90 for $280.
- Inkling Small is off the frontier: at the same or lower cost, GPT-5.6 Luna (xhigh) scores 34.80 for $179.
Gemini 3.7 Flash (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-3-7-flash/inkling-small · Markdown: /api/v1/compare/gemini-3-7-flash/inkling-small?format=md · llms.txt · agent skill