Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Codestral 2508 and Qwen2.5 72B Instruct, 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

Codestral 2508 vs Qwen2.5 72B Instruct

Live dataset updated 9/3/2026, 3:06:08 AM UTC

Open 1200×630 evidence receipt
Factual comparison of Codestral 2508 and Qwen2.5 72B Instruct
Field
Codestral 2508

Mistral AI

ModelCap position#218#180
Index score0.017.2
EvidenceEstimatedpublisher corpus prior · leave-one-anchor-out calibratedMeasured3 public benchmark observations across 3 boards
Input / 1M$0.30$0.36
Output / 1M$0.90$0.40
Pricing statusfreshfresh
Context256K33K
Providers12
Weight accessAPI onlyRestricted license

Decision facts

  • Codestral 2508 is #218; Qwen2.5 72B Instruct is #180 on the same current language board.
  • Index scores are 0.0 for Codestral 2508 and 17.2 for Qwen2.5 72B Instruct.
  • Evidence differs: Codestral 2508 is Estimated; Qwen2.5 72B Instruct is Measured.
  • Listed output price per 1M tokens is $0.90 for Codestral 2508 and $0.40 for Qwen2.5 72B Instruct.
  • Published context is 256,000 tokens for Codestral 2508 and 32,768 for Qwen2.5 72B Instruct.
  • Weight access differs: Codestral 2508 is none; Qwen2.5 72B Instruct is restricted.
  • ModelCap currently lists 1 providers for Codestral 2508 and 2 for Qwen2.5 72B Instruct.

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.