Swapping every model in a RAG

Automated excerpt

The models were frozen there on purpose: same embedder, same generator everywhere, so that only the framework could make a difference. The golden set grew from 10 questions on one topic to 100 across four topics. Every answer is scored by a Claude, a GPT and a Gemini judge, on purpose including the judge from the generator's own vendor. Note: the groundedness judge caught me before it caught any model. Every model refused every unanswerable question.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.