Benchmark RadarAI BENCHMARK PROFILE
CLUBench
CLUBench evaluates clustering algorithms across 131 datasets (tabular, text, image) using 24 algorithms, measuring clustering performance via standard metrics like NMI, ARI, etc.
- Released
- 2026-05-28
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
There is no comprehensive comparison of classical, deep, and foundation-model clustering methods. CLUBench provides systematic insights into algorithm selection and performance across data types.
Motivation
Clustering is a fundamental problem in data science with a long-standing research history, yielding numerous insightful algorithms.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.