Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Gemma 3 4B and Sonar, 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

Gemma 3 4B vs Sonar

Live dataset updated 8/17/2026, 11:13:20 PM UTC

Open 1200×630 evidence receipt
Factual comparison of Gemma 3 4B and Sonar
Field
Sonar

Perplexity

ModelCap position#195#196
Index score10.99.6
EvidenceMeasured3 public benchmark observations across 3 boardsMeasured1 public benchmark observation across 1 board
Input / 1M$0.05$1.00
Output / 1M$0.10$1.00
Pricing statusfreshfresh
Context131K127K
Providers11
Weight accessGated accessAPI only

Decision facts

  • Gemma 3 4B is #195; Sonar is #196 on the same current language board.
  • Index scores are 10.9 for Gemma 3 4B and 9.6 for Sonar.
  • Both positions use Measured evidence.
  • Listed output price per 1M tokens is $0.10 for Gemma 3 4B and $1.00 for Sonar.
  • Published context is 131,072 tokens for Gemma 3 4B and 127,072 for Sonar.
  • Weight access differs: Gemma 3 4B is gated; Sonar is none.

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.