AI screeners favor cover letters from certain AI models, independent of candidate quality
The audit pairs eleven LLM writers with nine API-hosted LLM evaluators across ten job descriptions and fifty candidates per job. Evaluators rank writer models in a consistent order, locally hosted models are systematically disadvantaged, and evaluators favour their own outputs. In the worst pairing, 1.8 out of twenty-five qualified candidates are filtered out purely because of model mismatch. The cause is stylistic cues that evaluators, often unanimously, reward or penalise.