Databricks says its Genie agent beats two frontier agents on a new enterprise benchmark
Overview
Databricks says its Genie data agent passed 91% of tasks on a new enterprise data-agent benchmark it built with Turing, against 45% and 58% for two frontier agents.
Genie also used fewer than half the tokens, which Databricks attributes to its Genie Ontology context layer.
The benchmark tests business questions in a live Databricks workspace. Databricks says access requires contacting its account team, who will help set it up. These results are Databricks' own claims and have not been independently verified.
Written by AI from the articles below · updated Nov 11, 10:21 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Databricks BlogOfficialDatabricks 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.
Heat Trend
- Current comparable heat
- 6
- Peak comparable heat
- 10Nov 11, 11:00 AM ET
- Change in past 24 hours
- –
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.