Skip to content
ModelCap

Model decision surface

Compare AI models

Start with HARC Llama 3.1 8B Instruct and MAI DS R1, 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

HARC Llama 3.1 8B Instruct vs MAI DS R1

Live dataset updated 9/15/2026, 5:33:33 AM UTC

Open 1200×630 evidence receipt
Factual comparison of HARC Llama 3.1 8B Instruct and MAI DS R1
Field
MAI DS R1

Microsoft

ModelCap position#190#95
Index score6.746.8
EvidenceInheritedmerge of meta-llama/llama-3.1-8b-instruct · merge (100%)Inheritedfinetune of deepseek/deepseek-r1 · finetune (100%)
Input / 1MUnavailableUnavailable
Output / 1MUnavailableUnavailable
Pricing statusunavailableunavailable
Context——
Providers00
Weight accessRestricted licenseOpen weights

Decision facts

  • HARC Llama 3.1 8B Instruct is #190; MAI DS R1 is #95 on the same current language board.
  • Index scores are 6.7 for HARC Llama 3.1 8B Instruct and 46.8 for MAI DS R1. 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.
  • Both positions use Inherited evidence.
  • Weight access differs: HARC Llama 3.1 8B Instruct is restricted; MAI DS R1 is open.

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.