Skip to content
ModelCap

Head-to-head comparison

Nemotron 3.5 Lightning vs Inkling Small

Nemotron 3.5 Lightning (NVIDIA) and Inkling Small (Thinking Machines) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 19 September 2026

As of 19 September 2026, Nemotron 3.5 Lightning holds the stronger ModelCap Index position (#82 vs #83); Nemotron 3.5 Lightning is 6× cheaper per output token ($0.20/1M vs $1.20/1M); Inkling Small offers the longer context window (1M vs 262K tokens); and Inkling Small ships open weights.

Which should you choose?

Choose Nemotron 3.5 Lightning if…

  • you want the stronger overall ModelCap Index position — #82 against #83 (51.9 vs 51.7 points).
  • API cost matters — $0.20/1M output tokens against $1.20/1M, about 6× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.07/1M against $0.45/1M.
  • you want provider choice — 4 listed API providers against 3.
  • you want the more recently listed model — Nemotron 3.5 Lightning was listed 11 August 2026, Inkling Small 30 July 2026.

Choose Inkling Small if…

  • you need the longer context window — 1M tokens against 262K.
  • you want to self-host: Inkling Small ships open weights while Nemotron 3.5 Lightning is restricted license.
  • AA Humanity's Last Exam is your yardstick — 33.3% against 10.6%.

Nemotron 3.5 Lightning vs Inkling Small: specs, pricing and context

Specification comparison of Nemotron 3.5 Lightning and Inkling Small
FieldNemotron 3.5 LightningNVIDIAInkling SmallThinking Machines
ModelCap Index position#82#83
Index score51.951.7
EvidenceMeasuredMeasured
Input price / 1M tokens$0.07$0.45
Output price / 1M tokens$0.20$1.20
Context window262K tokens1M tokens
Max output tokens236K262K
API providers listed43
Weight accessRestricted licenseOpen weights
Input modalitiesTextText, Image, Audio
First listed11 August 202630 July 2026
PublisherNVIDIAThinking Machines

Evidence: 1 public benchmark observation across 1 board · 4 public benchmark observations across 4 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Nemotron 3.5 Lightning vs Inkling Small

Public benchmark boards where Nemotron 3.5 Lightning or Inkling Small has a published result
BoardNemotron 3.5 LightningInkling SmallLeads
Arena codingArena (LMArena)—14741466–1483Only one result
LMArena AgentLMArena—-9.2%-10.5%–-7.8%Only one result
ARC-AGI-2ARC Prize Foundation—40.1%X-HighOnly one result
AA Intelligence IndexArtificial Analysis12.9intelligence-index:v4.3:reasoning-unspecified—Only one result
AA Humanity's Last ExamArtificial Analysis10.6%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Nemotron 3.5 Lightning":reasoning=true33.3%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Inkling Small":reasoning=trueInkling Small

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

Nemotron 3.5 Lightning vs Inkling Small: common questions

Is Nemotron 3.5 Lightning better than Inkling Small?

Nemotron 3.5 Lightning ranks higher on the ModelCap Index as of 19 September 2026: #82 against #83. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.

Is Nemotron 3.5 Lightning cheaper than Inkling Small?

Nemotron 3.5 Lightning is cheaper on output tokens: $0.20/1M against $1.20/1M. Input tokens are $0.07/1M for Nemotron 3.5 Lightning and $0.45/1M for Inkling Small. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.24 for Nemotron 3.5 Lightning versus $1.50 for Inkling Small. Nemotron 3.5 Lightning costs 84.0% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.

Which has the bigger context window, Nemotron 3.5 Lightning or Inkling Small?

Inkling Small has the larger context window: 1M tokens against 262K.

Which is better for coding, Nemotron 3.5 Lightning or Inkling Small?

The two models do not share a coding benchmark board on ModelCap yet, so no head-to-head coding score is published; the ModelCap Index position is the closest overall signal.

Are Nemotron 3.5 Lightning and Inkling Small open-weight models?

Nemotron 3.5 Lightning: Restricted license. Inkling Small: Open weights. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run Nemotron 3.5 Lightning and Inkling Small?

ModelCap currently lists 4 API providers for Nemotron 3.5 Lightning and 3 for Inkling Small, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Nemotron 3.5 Lightning vs Inkling Small comparison?

Every figure comes from the sealed ModelCap dataset published 19 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further