Benchmark RadarAI BENCHMARK PROFILE
TabQueryBench
TabQueryBench evaluates synthetic tabular data generators using SQL-shaped analytical queries as structural assessors, providing 44 reusable query templates across 49 datasets.
- Released
- 2026-07-04
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Existing synthetic data evaluations focus on statistical similarity and downstream ML utility, but rarely test analytical query structure. This benchmark addresses that gap, offering a way to assess query-centric fidelity for practical data analysis use cases.
Motivation
Synthetic tabular data support use cases like data sharing, model development under access restrictions, and rapid prototyping of analytical workflows.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.