Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Llama 4 Maverick and Phi 3.5 MoE instruct, 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

Llama 4 Maverick vs Phi 3.5 MoE instruct

Live dataset updated 9/22/2026, 10:37:09 PM UTC

Open 1200×630 evidence receipt
Factual comparison of Llama 4 Maverick and Phi 3.5 MoE instruct
Field
ModelCap position#167#165
Index score32.233.6
EvidenceMeasured3 public benchmark observations across 3 boardsEstimatedglobal-corpus-prior over 209 held-out anchors (42%); launch card against 4 resolved peers on 6 rows (58%); exceeds every named peer on 4 of 6 rows; optimism haircut 0.67 from cross-lab-probe; shrunk 16.7 up toward the measured corpus
Input / 1M$0.188Unavailable
Output / 1M$0.652Unavailable
Pricing statusfreshunavailable
Context1M—
Providers50
Weight accessGated accessOpen weights

Decision facts

  • Llama 4 Maverick is #167; Phi 3.5 MoE instruct is #165 on the same current language board.
  • Index scores are 32.2 for Llama 4 Maverick and 33.6 for Phi 3.5 MoE instruct. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
  • Evidence differs: Llama 4 Maverick is Measured; Phi 3.5 MoE instruct is Estimated.
  • Weight access differs: Llama 4 Maverick is gated; Phi 3.5 MoE instruct is open.
  • ModelCap currently lists 5 providers for Llama 4 Maverick and 0 for Phi 3.5 MoE instruct.

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.