AI & Agent Systems
Model Intelligence Maintainer
A workbook and guide comparing model quality, price and provider coverage.
What it is
A maintained workbook and static guide that answer one practical question: which model should actually be used, for what, and at what cost, based on multiple public benchmark sources.
A Python pipeline refreshes and normalises OpenRouter, Artificial Analysis, Vals and LiveBench data into deterministic datasets, a workbook and a deployed static guide, keeping provenance and cohort rules visible.