Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Hy4 preview and TCAndon Router, 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

Hy4 preview vs TCAndon Router

Live dataset updated 9/10/2026, 1:00:55 AM UTC

Open 1200×630 evidence receipt
Factual comparison of Hy4 preview and TCAndon Router
Field
ModelCap position#23#137
Index score71.830.5
EvidenceMeasured9 reported rows against measured corpus ladders (41%); publisher-corpus-prior over 183 held-out anchors (11%); opens above measured predecessor tencent/hy3 on same-family ordering evidence (39%); 1 specialist-board observation at 2.5% support (9%); shrunk 1.3 toward the measured corpusInheritedfinetune of Qwen/Qwen3-4B-Instruct-2507 · finetune (100%)
Input / 1M$0.834Unavailable
Output / 1M$2.50Unavailable
Pricing statusfreshunavailable
Context1M
Providers10
Weight accessOpen weightsOpen weights

Decision facts

  • Hy4 preview is #23; TCAndon Router is #137 on the same current language board.
  • Index scores are 71.8 for Hy4 preview and 30.5 for TCAndon Router. Their published uncertainty intervals do not overlap, but the aggregate Index does not predict performance on every task; compare the relevant benchmark configurations before choosing.
  • Evidence differs: Hy4 preview is Measured; TCAndon Router is Inherited.
  • ModelCap currently lists 1 providers for Hy4 preview and 0 for TCAndon Router.

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.