DA-bench

Visual Benchmark for Data Analytics AI Agents

Question II8: Can use NLQ feature engineering as part of an insight request

  • Prompt: Which zip code has the highest percentage of submitted customer complaints that have a neutral sentiment?
  • Category: Insight Identification
  • Datasets: Complaint Data

Latest Results

Tool Score Timestamp Video Recording
unsupervised 5 June 30, 2024 - 12:45 AM
Video Unavailable
databricks 0 June 17, 2024 - 11:48 PM
Video Unavailable
julius 5 June 9, 2024 - 01:46 AM
ChatGPT 5 July 10, 2024 - 03:32 PM
Video Unavailable