DeepSeek V3 (Dec '24) vs Inkling Small
Which is better for the money: DeepSeek V3 (Dec '24) by DeepSeek 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 17.2 points higher (25.7 vs 8.5) but costs 9.5× as much to run the benchmark ($241 vs $25.4; mid-range vs budget cost classes). They are not alternatives at one budget: pick Inkling Small when you need intelligence above 8.5, and DeepSeek V3 (Dec '24) when 8.5 is enough.
| Metric | DeepSeek V3 (Dec '24) | Inkling Small | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 8.5 | 25.7 | +202.4% Inkling Small is 3.0× more intelligent |
| Total AA cost (lower is better) | $25.37 | $240.85 | +849.3% Inkling Small is 9.5× more expensive |
| End-to-end time (lower is better) | 11.84s | 12.68s | +7.1% Inkling Small is 7.1% slower |
| Price per 1M tokens (in / out) | $0.32 / $0.89 | $0.30 / $1.20 | |
| Input modalities | Text | Text, Image, Speech |
Inkling Small vs DeepSeek V3 (Dec '24): 202.4% more intelligence, 849.3% more cost to run the AA benchmark, and 7.1% slower end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V3 (Dec '24) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- Inkling Small is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
DeepSeek V3 (Dec '24)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/deepseek-v3/inkling-small · Markdown: /api/v1/compare/deepseek-v3/inkling-small?format=md · llms.txt · agent skill