Tidalwave AI tops general models in mortgage underwriting accuracy benchmark
Posted onA joint study from mortgage technology platform Tidalwave and researchers at Columbia University found that Tidalwave’s mortgage-trained AI agent produced more accurate answers to loan underwriting questions than a general-purpose large language model. The benchmarking evaluated Tidalwave’s SOLO agent against Claude 4.5 from Anthropic on 90 questions commonly asked by loan officers during the mortgage […]