Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Hy3 and Hy4 preview, 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

Hy3 vs Hy4 preview

Live dataset updated 9/3/2026, 3:28:37 AM UTC

Open 1200×630 evidence receipt
Factual comparison of Hy3 and Hy4 preview
Field
Hy3

Tencent

ModelCap position#20#19
Index score68.568.6
EvidenceMeasured5 public benchmark observations across 5 boardsEstimatedplaced against measured peers on publisher-reported benchmarks, discounted for self-report optimism; floored directly above its measured family predecessor
Input / 1M$0.132$0.834
Output / 1M$0.528$2.50
Pricing statusfreshfresh
Context262K1M
Providers61
Weight accessOpen weightsOpen weights

Decision facts

  • Hy3 is #20; Hy4 preview is #19 on the same current language board.
  • Index scores are 68.5 for Hy3 and 68.6 for Hy4 preview.
  • Evidence differs: Hy3 is Measured; Hy4 preview is Estimated.
  • Listed output price per 1M tokens is $0.53 for Hy3 and $2.50 for Hy4 preview.
  • Published context is 262,144 tokens for Hy3 and 1,048,576 for Hy4 preview.
  • ModelCap currently lists 6 providers for Hy3 and 1 for Hy4 preview.

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.