Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Mistral Medium 3.5 and Hy3, 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

Mistral Medium 3.5 vs Hy3

Live dataset updated 8/18/2026, 3:36:20 AM UTC

Open 1200×630 evidence receipt
Factual comparison of Mistral Medium 3.5 and Hy3
Field
Hy3

Tencent

ModelCap position#38#18
Index score53.967.5
EvidenceMeasured4 public benchmark observations across 4 boardsMeasured5 public benchmark observations across 5 boards
Input / 1M$1.50$0.132
Output / 1M$7.50$0.528
Pricing statusfreshfresh
Context262K262K
Providers16
Weight accessAPI onlyOpen weights

Decision facts

  • Mistral Medium 3.5 is #38; Hy3 is #18 on the same current language board.
  • Index scores are 53.9 for Mistral Medium 3.5 and 67.5 for Hy3.
  • Both positions use Measured evidence.
  • Listed output price per 1M tokens is $7.50 for Mistral Medium 3.5 and $0.53 for Hy3.
  • Published context is 262,144 tokens for Mistral Medium 3.5 and 262,144 for Hy3.
  • Weight access differs: Mistral Medium 3.5 is none; Hy3 is open.
  • ModelCap currently lists 1 providers for Mistral Medium 3.5 and 6 for Hy3.

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.