# Classification on Datasets with a large number of classes (test)

Source: [Classification on Datasets with a large number of classes (test)](<https://www.sota2.com/research/sota/classification-on-datasets-with-a-large-number-of-classes-test>)

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

Data updated: 2026-02-26T05:51:51.911Z

Evaluation of general Classification performance across a specific collection of datasets characterized by a large number of classes, utilizing specialized ranking and Z-score metrics.

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 | Classification |
| Dataset (including any stated split) | Datasets with a large number of classes (test) |
| Metric | Mean Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Mean Accuracy](<https://www.sota2.com/research/sota/classification-on-datasets-with-a-large-number-of-classes-test.md?metric=Mean%20Accuracy>): Higher is better; unit: PERCENT.

- [Mean Rank](<https://www.sota2.com/research/sota/classification-on-datasets-with-a-large-number-of-classes-test.md?metric=Mean%20Rank>): Lower is better; unit: SCALAR.

- [Mean Z-Score](<https://www.sota2.com/research/sota/classification-on-datasets-with-a-large-number-of-classes-test.md?metric=Mean%20Z-Score>): Higher is better; unit: SCALAR.

- [Std. Z-Score](<https://www.sota2.com/research/sota/classification-on-datasets-with-a-large-number-of-classes-test.md?metric=Std.%20Z-Score>): Lower is better; unit: SCALAR.

- [Median Z-Score](<https://www.sota2.com/research/sota/classification-on-datasets-with-a-large-number-of-classes-test.md?metric=Median%20Z-Score>): Higher is better; unit: SCALAR.

- [Number of Wins](<https://www.sota2.com/research/sota/classification-on-datasets-with-a-large-number-of-classes-test.md?metric=Number%20of%20Wins>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Mean Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| XGBoost | 88.5 | Not recorded | 68fa75521e209131cea6722d |
| KNN | 78.9 | Not recorded | 68fa75521e209131cea6722d |
| CatBoost | 78.1 | Not recorded | 68fa75521e209131cea6722d |
| TuneTables | 77.9 | Not recorded | 68fa75521e209131cea6722d |
| rtdl\_ResNet | 77.6 | Not recorded | 68fa75521e209131cea6722d |
| Random Forest | 75.1 | Not recorded | 68fa75521e209131cea6722d |
| rtdl\_MLP | 62.4 | Not recorded | 68fa75521e209131cea6722d |

### XGBoost

Mean Accuracy: 88.5. Result ID: 69939add3a6c31484917326b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75521e209131cea6722d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62821e209131ce9f9b56.md>)

[Implementation](<https://github.com/dmlc/xgboost>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### KNN

Mean Accuracy: 78.9. Result ID: 69939add3a6c31484917326e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75521e209131cea6722d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CatBoost

Mean Accuracy: 78.1. Result ID: 69939add3a6c31484917326f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75521e209131cea6722d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65501e209131cea09938.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TuneTables

Mean Accuracy: 77.9. Result ID: 69939add3a6c31484917326c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75521e209131cea6722d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75521e209131cea6722d.md>)

[Implementation](<https://github.com/penfever/TuneTables>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### rtdl\_ResNet

Mean Accuracy: 77.6. Result ID: 69939add3a6c31484917326d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75521e209131cea6722d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71071e209131cea4eb08.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Random Forest

Mean Accuracy: 75.1. Result ID: 69939add3a6c314849173270.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75521e209131cea6722d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### rtdl\_MLP

Mean Accuracy: 62.4. Result ID: 69939add3a6c314849173271.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75521e209131cea6722d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71071e209131cea4eb08.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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