Databricks says Genie scores 91% on a new enterprise data-agent benchmark
AIDatabricks reports that Genie passed 91% of tasks on a new enterprise data-agent benchmark built with Turing, versus 45% and 58% for two frontier agents. Genie also used fewer than half the tokens, with Databricks crediting its Genie Ontology context layer for the gap.
Source details
Databricks Blog · databricks.comPublished · added here
Original title: Genie with Genie Ontology Delivers 1.6× the Accuracy with Less than Half the Tokens