Direct PT/DX × Bowers Enterprises · Phase 0 Validation
The LLM Vision Shootout
The assumption we're testing
Vision AI can reliably read clinical documents across every format Direct PT/DX receives.
Names, dates of birth, dates of service, CPT codes, unit counts — pulled from real scans and faxes. This one assumption carries the triage and reconciliation workflows.
Four models, head to head
Claude Sonnet 4.6Claude Opus 4.8GPT-5.5Gemini 3.1 Pro
The plan, in order
01Label the answer keyDebbie's team · ~2–3 hrs
02Build the test harnessChase
03Run every document through every modelSame prompt, no favorites
04Score accuracy, cost, and failure modesAgainst the answer key
05Deliver the shootout chartGo / no-go + model pick