Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Gemma 4 31B and GPT-5.3-Codex, 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 4 31B vs GPT-5.3-Codex

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

Open 1200×630 evidence receipt
Factual comparison of Gemma 4 31B and GPT-5.3-Codex
Field
ModelCap position#30#20
Index score60.066.4
EvidenceMeasured4 public benchmark observations across 4 boardsMeasured1 public benchmark observation across 1 board
Input / 1M$0.10$1.75
Output / 1M$0.34$14.00
Pricing statusfreshfresh
Context262K400K
Providers162
Weight accessOpen weightsAPI only

Decision facts

  • Gemma 4 31B is #30; GPT-5.3-Codex is #20 on the same current language board.
  • Index scores are 60.0 for Gemma 4 31B and 66.4 for GPT-5.3-Codex.
  • Both positions use Measured evidence.
  • Listed output price per 1M tokens is $0.34 for Gemma 4 31B and $14.00 for GPT-5.3-Codex.
  • Published context is 262,144 tokens for Gemma 4 31B and 400,000 for GPT-5.3-Codex.
  • Weight access differs: Gemma 4 31B is open; GPT-5.3-Codex is none.
  • ModelCap currently lists 16 providers for Gemma 4 31B and 2 for GPT-5.3-Codex.

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.