Onton Releases Ontology 1: A Neurosymbolic Search Model That is 2.7x More Accurate than the World’s Best E-commerce Search Engines
Onton released Ontology 1, a neurosymbolic search model claiming 2.7x accuracy over top e-commerce engines. Benchmarks using LLM judges showed a mean precision@10 of 0.630.
Onton has launched Ontology 1, a neurosymbolic AI model designed for complex product discovery. The system handles conversational and multimodal queries, aiming to improve how users find items within large catalogs.
Performance testing utilized a 90-query benchmark assessed by three independent LLM judges, yielding a mean precision@10 score of 0.630. The company states this represents a 2.7x accuracy improvement compared to leading e-commerce search engines.
Neurosymbolic approaches combine neural networks with symbolic reasoning, potentially offering better interpretability and logic than pure deep learning models. This release highlights a shift toward specialized AI architectures for vertical search applications rather than general-purpose chatbots.
This page provides an editorial summary based on publicly available information. It is not a republished article. Use the source link below for the original report.