Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Phi 3.5 MoE instruct and gpt-oss-20b, 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

Phi 3.5 MoE instruct vs gpt-oss-20b

Live dataset updated 9/22/2026, 3:10:38 AM UTC

Open 1200×630 evidence receipt
Factual comparison of Phi 3.5 MoE instruct and gpt-oss-20b
Field
ModelCap position#162#159
Index score32.033.5
EvidenceEstimatedglobal-corpus-prior over 203 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 16.8 up toward the measured corpusMeasured3 public benchmark observations across 3 boards
Input / 1MUnavailable$0.03
Output / 1MUnavailable$0.13
Pricing statusunavailablefresh
Context—131K
Providers012
Weight accessOpen weightsOpen weights

Decision facts

  • Phi 3.5 MoE instruct is #162; gpt-oss-20b is #159 on the same current language board.
  • Index scores are 32.0 for Phi 3.5 MoE instruct and 33.5 for gpt-oss-20b. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
  • Evidence differs: Phi 3.5 MoE instruct is Estimated; gpt-oss-20b is Measured.
  • ModelCap currently lists 0 providers for Phi 3.5 MoE instruct and 12 for gpt-oss-20b.

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.