Gemini 3.8 Flash (medium) vs Inkling (xhigh)
Which is better for the money: Gemini 3.8 Flash (medium) by Google or Inkling (xhigh) 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 3.8 Flash (medium) scores 14.5 points higher (40.0 vs 25.5) but costs 1.1× as much to run the benchmark ($1100 vs $1026; both premium class). Pick Gemini 3.8 Flash (medium) when the extra intelligence is worth the premium, otherwise Inkling (xhigh).
| Metric | Gemini 3.8 Flash (medium) | Inkling (xhigh) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 40.0 | 25.5 | −36.3% Inkling (xhigh) is 36.3% less intelligent |
| Total AA cost (lower is better) | $1,100.06 | $1,026.14 | −6.7% Inkling (xhigh) is 6.7% cheaper |
| End-to-end time (lower is better) | 10.32s | 37.45s | +262.9% Inkling (xhigh) is 262.9% slower |
| Price per 1M tokens (in / out) | $0.75 / $3.75 | $1.00 / $4.05 | |
| Input modalities | Not reported | Not reported |
Inkling (xhigh) vs Gemini 3.8 Flash (medium): 36.3% less intelligence, 6.7% less cost to run the AA benchmark, and 262.9% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Gemini 3.8 Flash (medium) is off the frontier: at the same or lower cost, GLM-5.3-Flash scores 41.90 for $280.
- Inkling (xhigh) is off the frontier: at the same or lower cost, GLM-5.3-Flash scores 41.90 for $280.
Gemini 3.8 Flash (medium)Inkling (xhigh)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/gemini-3-8-flash-medium/inkling · Markdown: /api/v1/compare/gemini-3-8-flash-medium/inkling?format=md · llms.txt · agent skill