Inkling Small vs Mistral Large 4 Preview
Which is better for the money: Inkling Small by Thinking Machines or Mistral Large 4 Preview by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
Mistral Large 4 Preview scores 12.7 points higher (38.4 vs 25.7) but costs 6.7× as much to run the benchmark ($1608 vs $241; premium vs mid-range cost classes). They are not alternatives at one budget: pick Mistral Large 4 Preview when you need intelligence above 25.7, and Inkling Small when 25.7 is enough.
| Metric | Inkling Small | Mistral Large 4 Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 25.7 | 38.4 | +49.4% Mistral Large 4 Previ… is 49.4% more intelligent |
| Total AA cost (lower is better) | $240.85 | $1,607.86 | +567.6% Mistral Large 4 Previ… is 6.7× more expensive |
| End-to-end time (lower is better) | 12.67s | 27.12s | +114.0% Mistral Large 4 Previ… is 114.0% slower |
| Price per 1M tokens (in / out) | $0.30 / $1.20 | $1.36 / $4.18 | |
| Input modalities | Text, Image, Speech | Text, Image |
Mistral Large 4 Preview vs Inkling Small: 49.4% more intelligence, 567.6% more cost to run the AA benchmark, and 114.0% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Inkling Small is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- Mistral Large 4 Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Inkling SmallMistral Large 4 PreviewToday'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/inkling-small/mistral-large-4 · Markdown: /api/v1/compare/inkling-small/mistral-large-4?format=md · llms.txt · agent skill