Skip to content
ModelCap

Model decision surface

Compare AI models

Start with GPT-5.6 Luna and GPT-6 Astra, 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

GPT-5.6 Luna vs GPT-6 Astra

Live dataset updated 9/9/2026, 9:50:24 PM UTC

Open 1200×630 evidence receipt
Factual comparison of GPT-5.6 Luna and GPT-6 Astra
Field
ModelCap position#26#1
Index score71.395.7
EvidenceMeasured6 public benchmark observations across 6 boardsMeasured4 public benchmark observations across 4 boards
Input / 1M$0.20$10.00
Output / 1M$1.20$50.00
Pricing statusfreshfresh
Context1M1M
Providers32
Weight accessAPI onlyAPI only

Decision facts

  • GPT-5.6 Luna is #26; GPT-6 Astra is #1 on the same current language board.
  • Index scores are 71.3 for GPT-5.6 Luna and 95.7 for GPT-6 Astra. 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 $1.20 for GPT-5.6 Luna and $50.00 for GPT-6 Astra. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $1.00 for GPT-5.6 Luna versus $45.00 for GPT-6 Astra. GPT-5.6 Luna costs 97.8% 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 1,050,000 tokens for GPT-5.6 Luna and 1,050,000 for GPT-6 Astra.
  • ModelCap currently lists 3 providers for GPT-5.6 Luna and 2 for GPT-6 Astra.

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.