Skip to content
ModelCap

Model decision surface

Compare AI models

Start with K2 Horizon 375B A23B and KAT Coder V2.5 Dev, 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

K2 Horizon 375B A23B vs KAT Coder V2.5 Dev

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

Open 1200×630 evidence receipt
Factual comparison of K2 Horizon 375B A23B and KAT Coder V2.5 Dev
Field
ModelCap position#34#35
Index score66.566.2
EvidenceEstimatedglobal-corpus-prior over 183 held-out anchors (24%); launch card against 7 resolved peers on 11 rows (76%); optimism haircut 0 from cross-lab-probe; shrunk 4.1 toward the measured corpusEstimatedglobal-corpus-prior over 183 held-out anchors (22%); launch card against 2 resolved peers on 4 rows (79%); exceeds every named peer on 4 of 4 rows; optimism haircut 0 from cross-lab-probe; shrunk 3.4 toward the measured corpus
Input / 1MUnavailableUnavailable
Output / 1MUnavailableUnavailable
Pricing statusunavailableunavailable
Context——
Providers00
Weight accessOpen weightsOpen weights

Decision facts

  • K2 Horizon 375B A23B is #34; KAT Coder V2.5 Dev is #35 on the same current language board.
  • Index scores are 66.5 for K2 Horizon 375B A23B and 66.2 for KAT Coder V2.5 Dev. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
  • Both positions use Estimated evidence.

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.