Property Finder removes model-biased labels and cuts Bedrock vision costs by 86 per cent
Property Finder and AWS found that 96.8 per cent of a vision evaluation set had inherited labels from the incumbent model, structurally favouring it over alternatives. After independent expert annotation and iterative prompt optimisation on Amazon Bedrock, the company selected Llama 4 Maverick, reporting higher accuracy, 40–60 per cent lower latency and an estimated 86 per cent cost reduction.