Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Nemotron 3.5 Lightning and Inkling Small, or choose any two current ranked language models. Compare capability evidence, price, context, provider availability, and weight access without pretending one field decides every use case.

Current public data

Nemotron 3.5 Lightning vs Inkling Small

Live dataset updated 9/19/2026, 11:04:59 PM UTC

Open 1200×630 evidence receipt
Factual comparison of Nemotron 3.5 Lightning and Inkling Small
Field
Inkling Small

Thinking Machines

ModelCap position#82#83
Index score51.951.7
EvidenceMeasured1 public benchmark observation across 1 boardMeasured4 public benchmark observations across 4 boards
Input / 1M$0.07$0.45
Output / 1M$0.20$1.20
Pricing statusfreshfresh
Context262K1M
Providers43
Weight accessRestricted licenseOpen weights

Decision facts

  • Nemotron 3.5 Lightning is #82; Inkling Small is #83 on the same current language board.
  • Index scores are 51.9 for Nemotron 3.5 Lightning and 51.7 for Inkling Small. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
  • Both positions use Measured evidence.
  • Listed output price per 1M tokens is $0.20 for Nemotron 3.5 Lightning and $1.20 for Inkling Small. 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.
  • Published context is 262,144 tokens for Nemotron 3.5 Lightning and 1,048,576 for Inkling Small.
  • Weight access differs: Nemotron 3.5 Lightning is restricted; Inkling Small is open.
  • ModelCap currently lists 4 providers for Nemotron 3.5 Lightning and 3 for Inkling Small.

These are separate published fields, not a synthetic winner. ModelCap does not collapse price, access, context, and capability evidence into a hidden recommendation score.

Each comparison page is a permanent, shareable URL with the same live figures as this tool: ModelCap Index position, API pricing, context window, provider count, weight access and every shared benchmark board.