DA-bench

Visual Benchmark for Data Analytics AI Agents

Question L1: Can remember the meanings of oddly-named columns

  • Prompt: Turn 1: tw_cid should be referred to as 'TelecomWest Customer ID'. How many customers have a TelecomWest Customer ID? Turn 2: "What is the average churn rate for customers with a TelecomWest Customer ID?"
  • Category:
  • Datasets: Telco w/ Feature Eng

Latest Results

Tool Score Timestamp Video Recording
unsupervised 5
databricks 5
tableau -5
snowflake 5
chatgpt -5
julius -5
thoughtspot 0
microstrategy 5
qlik 0
Video Unavailable
sap 0
Video Unavailable
ibm 0
quicksight 0
Video Unavailable
bigquery -5