Inkling Small vs Nemotron 3.5 Lightning
Which is better for the money: Inkling Small by Thinking Machines or Nemotron 3.5 Lightning by NVIDIA? 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 12.8 points higher (25.7 vs 12.9) but costs 2.6× as much to run the benchmark ($241 vs $92.8; both mid-range class). Pick Inkling Small when the extra intelligence is worth the premium, otherwise Nemotron 3.5 Lightning.
| Metric | Inkling Small | Nemotron 3.5 Lightning | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 25.7 | 12.9 | −49.8% Nemotron 3.5 Lightning is 49.8% less intelligent |
| Total AA cost (lower is better) | $240.85 | $92.76 | −61.5% Nemotron 3.5 Lightning is 61.5% cheaper |
| End-to-end time (lower is better) | 12.95s | 8.98s | −30.7% Nemotron 3.5 Lightning is 30.7% faster |
| Price per 1M tokens (in / out) | $0.30 / $1.20 | $0.06 / $0.20 | |
| Input modalities | Text, Image, Speech | Text |
Nemotron 3.5 Lightning vs Inkling Small: 49.8% less intelligence, 61.5% less cost to run the AA benchmark, and 30.7% faster 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.
- Nemotron 3.5 Lightning is off the frontier: at the same or lower cost, GPT-6 Luna (Xhigh) scores 34.60 for $66.8.
Inkling SmallNemotron 3.5 LightningToday'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/nemotron-3-5-lightning · Markdown: /api/v1/compare/inkling-small/nemotron-3-5-lightning?format=md · llms.txt · agent skill