Profile and assess data quality

Activity 5 of 8 in Data quality · Occupation: Data quality analyst

The outcome: profiles and assesses critical data elements over stated populations.

Builds on: Select the critical data elements, Derive data quality rules.

Which AI model is best at profile and assess data quality?

Model	Provider	Tier	Test score	Knobits mastered (expected)	Cost per test run
gemini-4-argon	Google	Flagship	–	77%	$0.021
gemini-3.5-flash-lite	Google	Low cost	–	52%	$0.003
gpt-6-luna	OpenAI	Low cost	–	68%	$0.002
claude-haiku-5-5	Anthropic	Low cost	–	66%	$0.006

Test score: mean rubric score on the test tasks for this activity. Knobits mastered: expected share of the activity's knobits the model masters. Cost: mean API cost of one test run at list prices, half price for answers sent as a batch. Method and caveats.

The 10 knobits of this activity

2 that AI does well, 2 it does partly, and 6 where people still lead.

ID	Knobit	Type	AI exposure (models mastering)
Q-401	Recognises a null counted as missing where the element does not apply	Skill	People still lead 1/4
Q-402	Recognises a profiling sample excluding the problem population	Skill	People still lead 0/4
Q-403	Recognises a quality measurement labelled with a characteristic it does not test	Skill	People still lead 1/4
Q-404	Recognises a placeholder value counted as present	Skill	People still lead 0/4
Q-405	Recognises a quality ratio with no population, numerator or denominator	Skill	People still lead 1/4
Q-406	Recognises one quality ratio over differing populations	Skill	AI does this partly 2/4
Q-451	Explains the ISO/IEC 25012 data quality characteristics	Knowledge	AI does this well 3/4
Q-452	Explains data profiling methods	Knowledge	People still lead 0/4
Q-453	Explains ISO/IEC 25024 data quality measures	Knowledge	AI does this partly 2/4
Q-1901	Explains a pooled rate as the weighted mean of its population rates	Knowledge	AI does this well 4/4