GP versus the Specialist: a measured model-tier scorecard

MIS 752 Lab 4. A measured comparison of model tiers on five clinical questions (oncology staging, cardiology guideline, drug-drug interaction, rare-disease workup, ontology mapping) called through OpenRouter, plus a local Qwen/Qwen2.5-0.5B-Instruct temperature sweep. data/ holds the per-answer…

Description excerpted from the original listing, which is linked below.