# Classification on OpenML-cc18 (Average Rank Metric)

Source: [Classification on OpenML-cc18 (Average Rank Metric)](<https://www.sota2.com/research/sota/classification-on-openml-cc18-average-rank-metric>)

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

Data updated: 2026-06-04T12:12:52.009Z

Evaluation of general classification performance on the OpenML-cc18 dataset, measured using the Average Rank metric combining AUC, Accuracy, and F1 scores.

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) | OpenML-cc18 |
| Metric | Average Rank (AUC, Acc, F1) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 33 of 33 |
| 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

- [Average Rank (AUC, Acc, F1)](<https://www.sota2.com/research/sota/classification-on-openml-cc18-average-rank-metric.md?metric=Average%20Rank%20(AUC%2C%20Acc%2C%20F1)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Average Rank (AUC, Acc, F1) | Result date | Report paper |
| --- | --- | --- | --- |
| LimiX-16M | 4.99 | Not recorded | 6a2106f9c10484bac23f06cd |
| LimiX-2M | 5.83 | Not recorded | 6a2106f9c10484bac23f06cd |
| AutoGluon | 7.79 | Not recorded | 6a2106f9c10484bac23f06cd |
| TabPFN-v2 | 8.56 | Not recorded | 6a2106f9c10484bac23f06cd |
| RealMLP | 9.36 | Not recorded | 6a2106f9c10484bac23f06cd |
| TabICL | 10.04 | Not recorded | 6a2106f9c10484bac23f06cd |
| TabM | 10.75 | Not recorded | 6a2106f9c10484bac23f06cd |
| LightGBM | 11.16 | Not recorded | 6a2106f9c10484bac23f06cd |
| XGBoost | 11.51 | Not recorded | 6a2106f9c10484bac23f06cd |
| ExcelFormer | 14.21 | Not recorded | 6a2106f9c10484bac23f06cd |
| CatBoost | 14.27 | Not recorded | 6a2106f9c10484bac23f06cd |
| ResNet | 14.72 | Not recorded | 6a2106f9c10484bac23f06cd |
| RF | 14.89 | Not recorded | 6a2106f9c10484bac23f06cd |
| TANGOS | 14.91 | Not recorded | 6a2106f9c10484bac23f06cd |
| Mitra | 15.24 | Not recorded | 6a2106f9c10484bac23f06cd |
| TabR | 15.83 | Not recorded | 6a2106f9c10484bac23f06cd |
| MLP | 16.01 | Not recorded | 6a2106f9c10484bac23f06cd |
| T2G-Former | 16.49 | Not recorded | 6a2106f9c10484bac23f06cd |
| ET | 17.07 | Not recorded | 6a2106f9c10484bac23f06cd |
| MLP-PLR | 17.23 | Not recorded | 6a2106f9c10484bac23f06cd |
| ModernNCA | 17.47 | Not recorded | 6a2106f9c10484bac23f06cd |
| FT-Transformer | 17.74 | Not recorded | 6a2106f9c10484bac23f06cd |
| AutoInt | 19.87 | Not recorded | 6a2106f9c10484bac23f06cd |
| DANets | 19.89 | Not recorded | 6a2106f9c10484bac23f06cd |
| DCN-v2 | 19.94 | Not recorded | 6a2106f9c10484bac23f06cd |
| TabCaps | 22.34 | Not recorded | 6a2106f9c10484bac23f06cd |
| SNN | 22.49 | Not recorded | 6a2106f9c10484bac23f06cd |
| SwitchTab | 23.37 | Not recorded | 6a2106f9c10484bac23f06cd |
| TabTransformer | 24.05 | Not recorded | 6a2106f9c10484bac23f06cd |
| SAINT | 25.98 | Not recorded | 6a2106f9c10484bac23f06cd |
| TabNet | 26.4 | Not recorded | 6a2106f9c10484bac23f06cd |
| NODE | 26.64 | Not recorded | 6a2106f9c10484bac23f06cd |
| GrowNet | 27.94 | Not recorded | 6a2106f9c10484bac23f06cd |

### LimiX-16M

Average Rank (AUC, Acc, F1): 4.99. Result ID: 6a216baafbc373592c1e71f7.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

Recorded evaluation configuration: {"Number of Parameters":"16.52M"}. This record does not assert independent reproduction.

### LimiX-2M

Average Rank (AUC, Acc, F1): 5.83. Result ID: 6a216baafbc373592c1e71fb.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

Recorded evaluation configuration: {"Number of Parameters":"1.92M"}. This record does not assert independent reproduction.

### AutoGluon

Average Rank (AUC, Acc, F1): 7.79. Result ID: 6a216baafbc373592c1e71fc.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### TabPFN-v2

Average Rank (AUC, Acc, F1): 8.56. Result ID: 6a216baafbc373592c1e71fa.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

Recorded evaluation configuration: {"Number of Parameters":"7.24M"}. This record does not assert independent reproduction.

### RealMLP

Average Rank (AUC, Acc, F1): 9.36. Result ID: 6a216baafbc373592c1e71eb.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### TabICL

Average Rank (AUC, Acc, F1): 10.04. Result ID: 6a216baafbc373592c1e71f9.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c51e209131cea7a684.md>)

Recorded evaluation configuration: {"Number of Parameters":"27.10M"}. This record does not assert independent reproduction.

### TabM

Average Rank (AUC, Acc, F1): 10.75. Result ID: 6a216baafbc373592c1e71f3.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### LightGBM

Average Rank (AUC, Acc, F1): 11.16. Result ID: 6a216baafbc373592c1e71dd.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### XGBoost

Average Rank (AUC, Acc, F1): 11.51. Result ID: 6a216baafbc373592c1e71de.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.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.

### ExcelFormer

Average Rank (AUC, Acc, F1): 14.21. Result ID: 6a216baafbc373592c1e71e3.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### CatBoost

Average Rank (AUC, Acc, F1): 14.27. Result ID: 6a216baafbc373592c1e71dc.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

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

### ResNet

Average Rank (AUC, Acc, F1): 14.72. Result ID: 6a216baafbc373592c1e71ec.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### RF

Average Rank (AUC, Acc, F1): 14.89. Result ID: 6a216baafbc373592c1e71ea.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### TANGOS

Average Rank (AUC, Acc, F1): 14.91. Result ID: 6a216baafbc373592c1e71f1.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### Mitra

Average Rank (AUC, Acc, F1): 15.24. Result ID: 6a216baafbc373592c1e71f8.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fefc643ef7ccd74e5c526c.md>)

Recorded evaluation configuration: {"Number of Parameters":"75.67M"}. This record does not assert independent reproduction.

### TabR

Average Rank (AUC, Acc, F1): 15.83. Result ID: 6a216baafbc373592c1e71f5.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### MLP

Average Rank (AUC, Acc, F1): 16.01. Result ID: 6a216baafbc373592c1e71e6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### T2G-Former

Average Rank (AUC, Acc, F1): 16.49. Result ID: 6a216baafbc373592c1e71f0.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### ET

Average Rank (AUC, Acc, F1): 17.07. Result ID: 6a216baafbc373592c1e71e2.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### MLP-PLR

Average Rank (AUC, Acc, F1): 17.23. Result ID: 6a216baafbc373592c1e71e7.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### ModernNCA

Average Rank (AUC, Acc, F1): 17.47. Result ID: 6a216baafbc373592c1e71e8.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### FT-Transformer

Average Rank (AUC, Acc, F1): 17.74. Result ID: 6a216baafbc373592c1e71e4.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

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

### AutoInt

Average Rank (AUC, Acc, F1): 19.87. Result ID: 6a216baafbc373592c1e71df.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### DANets

Average Rank (AUC, Acc, F1): 19.89. Result ID: 6a216baafbc373592c1e71e0.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### DCN-v2

Average Rank (AUC, Acc, F1): 19.94. Result ID: 6a216baafbc373592c1e71e1.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### TabCaps

Average Rank (AUC, Acc, F1): 22.34. Result ID: 6a216baafbc373592c1e71f2.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### SNN

Average Rank (AUC, Acc, F1): 22.49. Result ID: 6a216baafbc373592c1e71ee.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### SwitchTab

Average Rank (AUC, Acc, F1): 23.37. Result ID: 6a216baafbc373592c1e71ef.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### TabTransformer

Average Rank (AUC, Acc, F1): 24.05. Result ID: 6a216baafbc373592c1e71f6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68f41e209131cea1f426.md>)

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

### SAINT

Average Rank (AUC, Acc, F1): 25.98. Result ID: 6a216baafbc373592c1e71ed.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0a1e209131cea25ade.md>)

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

### TabNet

Average Rank (AUC, Acc, F1): 26.4. Result ID: 6a216baafbc373592c1e71f4.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68db1e209131cea1eb45.md>)

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

### NODE

Average Rank (AUC, Acc, F1): 26.64. Result ID: 6a216baafbc373592c1e71e9.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.md>)

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

### GrowNet

Average Rank (AUC, Acc, F1): 27.94. Result ID: 6a216baafbc373592c1e71e5.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06cd.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.
