DA-bench

Visual Benchmark for Data Analytics AI Agents

Run #122

  • Tool: unsupervised
  • Date Tested: November 12, 2024
  • Setup Score: 100.0%
  • Verified Connects to Data Warehouse
  • Verified No Individual Upload of Files
  • Verified No SQL for Setup
  • Verified Setup Less Than Ten Minutes

See how this tool was set up for the test.


DA-bench Results for Run #122 — Percentage Test Score: 37.2% (80 / 215)

Data Querying (75 / 120)
Question Date Tested Score Video Recording

dq01
Perform an aggregation on an explicit column

November 12, 2024 5

dq02
Perform an aggregation with an explicit table but not an inferred column

November 12, 2024 5

dq03
Perform an aggregation with an implicit table and implicit column

November 12, 2024 5

dq04
Find and compare information across tables without joins

November 12, 2024 5

dq05
Work with non-literal values

November 12, 2024 5

dq06
Work with non-literal values and non-SQL data manipulation

November 12, 2024 5

dq07
Deal with common acronymns and more advanced aggregations

November 12, 2024 0

dq08
Multi-step queries

November 12, 2024 5

dq09
Aggregations with numeric predicates to filter

November 12, 2024 5

dq10
Aggregations with categorical predicates to filter

November 12, 2024 5

dq11
Schema review

November 12, 2024 5

dq12
Aggregate records that are filtered with a predicate requiring a join

November 12, 2024 -5

dq13
Recognizes truly ambiguous queries.

November 12, 2024 -5

dq14
Can handle boolean features

November 12, 2024 5

dq15
Handles ambiguous column names

November 12, 2024 -5

dq16
Understands set operates require consideration of overlap

November 12, 2024 -5

dq17
Finds relevant values inside a Column to answer questions

November 12, 2024 5

dq18
Lookup a single record by ID

November 12, 2024 5

dq19
Perform an aggregation by a different name and a second query from that

November 12, 2024 5

dq20
Perform an aggregation based on a very different question name

November 12, 2024 5

dq21
Perform a filter and an unusually-phrased aggregation in the correct order

November 12, 2024 5

dq23
Can handle typos well

November 12, 2024 5

dq24
Schema review

November 12, 2024 5

dq25
Work with non-literal values

November 12, 2024 5
Domain Knowledge (5 / 5)
Question Date Tested Score Video Recording

dk01
Column Relevance Determination

November 12, 2024 5
Feature Engineering (5 / 40)
Question Date Tested Score Video Recording

fe1
Make a boolean indicator feature for a criteria set

November 12, 2024 0

fe2
Make a categorical feature from a criteria set

November 12, 2024 0

fe3
Minmax normalization

November 12, 2024 0

fe4
Combining two input columns

November 12, 2024 5

fe5
Sentiment

November 12, 2024 0

fe6
Phrase Identification in Text

November 12, 2024 0

fe7
Advanced NLQ

November 12, 2024 0

fe8
Advanced NLQ

November 12, 2024 0
Insight Identification (-5 / 25)
Question Date Tested Score Video Recording

ii2
Compare an aggregation for two distinct subsets of data

November 12, 2024 5

ii5
Identifying basic trends on short timelines

November 12, 2024 0

ii6
Understands statistical significance

November 12, 2024 0

ii7
Understands derivitives

November 12, 2024 -5

ii8
Can use NLQ feature engineering as part of an insight request

November 12, 2024 -5
Learning (0 / 10)
Question Date Tested Score Video Recording

l1
Can remember the meanings of oddly-named columns

November 12, 2024 -5

l2
Can remember criteria sets under a single name

November 12, 2024 5
Visualization (0 / 15)
Question Date Tested Score Video Recording

v1
Basic Charting

November 12, 2024 0

v2
Charting with two series

November 12, 2024 0

v3
Categorical Charts

November 12, 2024 0