# Clustering on 20NG

Source: [Clustering on 20NG](<https://www.sota2.com/research/sota/clustering-on-20ng>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-10T00:38:18.948Z

Evaluation of general Clustering performance on the 20 Newsgroups (20NG) dataset, measured using Adjusted Rand Index (ARI) and Normalized Mutual Information (NMI).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Clustering |
| Dataset (including any stated split) | 20NG |
| Metric | ARI |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [ARI](<https://www.sota2.com/research/sota/clustering-on-20ng.md?metric=ARI>): Higher is better; unit: SCALAR.

- [NMI](<https://www.sota2.com/research/sota/clustering-on-20ng.md?metric=NMI>): Higher is better; unit: SCALAR.

## Recorded results

| Method | ARI | Result date | Report paper |
| --- | --- | --- | --- |
| K-means | 0.845 | Not recorded | 69d732bb7d0172140ec76d31 |
| DIVI-Info | 0.759 | Not recorded | 69d732bb7d0172140ec76d31 |
| GMM | 0.718 | Not recorded | 69d732bb7d0172140ec76d31 |
| SPKM | 0.514 | Not recorded | 69d732bb7d0172140ec76d31 |

### K-means

ARI: 0.845. Result ID: 69d8452847f34ce924c06491.

[Reporting paper](<https://www.sota2.com/research/paper/69d732bb7d0172140ec76d31.md>)

Recorded evaluation configuration: {"Time (s)":"0.40 (0.02)","Final K":"4.0 (0.0)"}. This record does not assert independent reproduction.

### DIVI-Info

ARI: 0.759. Result ID: 69d8452847f34ce924c06490.

[Reporting paper](<https://www.sota2.com/research/paper/69d732bb7d0172140ec76d31.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d732bb7d0172140ec76d31.md>)

Recorded evaluation configuration: {"Time (s)":"16.49 (1.03)","Final K":"4.0 (0.0)","Active dims":"351.6 (1.1)"}. This record does not assert independent reproduction.

### GMM

ARI: 0.718. Result ID: 69d8452847f34ce924c06492.

[Reporting paper](<https://www.sota2.com/research/paper/69d732bb7d0172140ec76d31.md>)

Recorded evaluation configuration: {"Time (s)":"1.42 (0.15)","Final K":"4.0 (0.0)"}. This record does not assert independent reproduction.

### SPKM

ARI: 0.514. Result ID: 69d8452847f34ce924c06493.

[Reporting paper](<https://www.sota2.com/research/paper/69d732bb7d0172140ec76d31.md>)

Recorded evaluation configuration: {"Time (s)":"7.98 (0.61)","Final K":"4.0 (0.0)","Active dims":"30.0 (0.0)"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.