GPT-6 Luna (Low) vs Inkling Small
Which is better for the money: GPT-6 Luna (Low) by OpenAI 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 4.2 points higher (25.7 vs 21.5) but costs 23× as much to run the benchmark ($241 vs $10.6; mid-range vs budget cost classes). They are not alternatives at one budget: pick Inkling Small when you need intelligence above 21.5, and GPT-6 Luna (Low) when 21.5 is enough.
| Metric | GPT-6 Luna (Low) | Inkling Small | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 21.5 | 25.7 | +19.5% Inkling Small is 19.5% more intelligent |
| Total AA cost (lower is better) | $10.63 | $240.85 | +2165.8% Inkling Small is 23× more expensive |
| End-to-end time (lower is better) | 6.75s | 12.95s | +91.9% Inkling Small is 91.9% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.30 / $1.20 | |
| Input modalities | Text, Image | Text, Image, Speech |
Inkling Small vs GPT-6 Luna (Low): 19.5% more intelligence, 2165.8% more cost to run the AA benchmark, and 91.9% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (Low) is on today's frontier: nothing is both smarter and cheaper.
- Inkling Small is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
GPT-6 Luna (Low)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/gpt-6-luna-low/inkling-small · Markdown: /api/v1/compare/gpt-6-luna-low/inkling-small?format=md · llms.txt · agent skill