dotnetspark/fbc-model-routing-benchmark

Measuring which LLM tier (foundation / instruction-tuned / SLM) you actually need for Florida Building Code lookups — with and without RAG grounding. Reproducible benchmark harness + citation-hallucination analysis. Built as a hands-on tutorial series on modern AI system design.

1 best points · 0 comments · 1 Hacker News post · 0 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: A model-routing benchmark – the routers optimize the wrong axis (1 points, 0 comments, by yadellopez, 2026-07-18)