# Text Classification on R52 small-scale (test)

Source: [Text Classification on R52 small-scale (test)](<https://www.sota2.com/research/sota/text-classification-on-r52-small-scale-test>)

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

Data updated: 2026-02-26T05:27:55.179Z

Evaluation of Text Classification performance on the small-scale test split of the R52 dataset, measured using accuracy.

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 | Text Classification |
| Dataset (including any stated split) | R52 small-scale (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/text-classification-on-r52-small-scale-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| HDGCN | 96.57 | Not recorded | 68fa6a1e1e209131cea26089 |
| BERT-base | 96.37 | Not recorded | 68fa6a1e1e209131cea26089 |
| HDGCN-static | 95.49 | Not recorded | 68fa6a1e1e209131cea26089 |
| TextING | 95.48 | Not recorded | 68fa6a1e1e209131cea26089 |
| GraphCNN | 94.6 | Not recorded | 68fa6a1e1e209131cea26089 |
| TextGCN | 93.56 | Not recorded | 68fa6a1e1e209131cea26089 |
| minCUT | 93.53 | Not recorded | 68fa6a1e1e209131cea26089 |
| SWEM | 92.94 | Not recorded | 68fa6a1e1e209131cea26089 |
| fastText | 92.81 | Not recorded | 68fa6a1e1e209131cea26089 |
| TextRNN | 90.54 | Not recorded | 68fa6a1e1e209131cea26089 |
| TextCNN | 87.59 | Not recorded | 68fa6a1e1e209131cea26089 |

### HDGCN

Accuracy: 96.57. Result ID: 698e0f3effc3901de09a7b09.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26089.md>)

[Implementation](<https://github.com/MathIsAll/HDGCN-pytorch>)

Recorded evaluation configuration: {"initialization":"300-d GloVe"}. This record does not assert independent reproduction.

### BERT-base

Accuracy: 96.37. Result ID: 698e0f3effc3901de09a7b07.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67531e209131cea157a0.md>)

Recorded evaluation configuration: {"source":"(Jin et al., 2019)"}. This record does not assert independent reproduction.

### HDGCN-static

Accuracy: 95.49. Result ID: 698e0f3effc3901de09a7b08.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26089.md>)

[Implementation](<https://github.com/MathIsAll/HDGCN-pytorch>)

Recorded evaluation configuration: {"initialization":"300-d GloVe","mode":"static"}. This record does not assert independent reproduction.

### TextING

Accuracy: 95.48. Result ID: 698e0f3effc3901de09a7b06.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa678e1e209131cea16f9b.md>)

Recorded evaluation configuration: {"source":"(Zhang et al., 2020b)"}. This record does not assert independent reproduction.

### GraphCNN

Accuracy: 94.6. Result ID: 698e0f3effc3901de09a7b04.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa678e1e209131cea16f9b.md>)

Recorded evaluation configuration: {"source":"(Zhang et al., 2020b)"}. This record does not assert independent reproduction.

### TextGCN

Accuracy: 93.56. Result ID: 698e0f3effc3901de09a7b03.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa678e1e209131cea16f9b.md>)

Recorded evaluation configuration: {"source":"(Zhang et al., 2020b)"}. This record does not assert independent reproduction.

### minCUT

Accuracy: 93.53. Result ID: 698e0f3effc3901de09a7b05.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68f81e209131cea1f661.md>)

Recorded evaluation configuration: {"source":"(Bianchi et al., 2019)"}. This record does not assert independent reproduction.

### SWEM

Accuracy: 92.94. Result ID: 698e0f3effc3901de09a7b02.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa678e1e209131cea16f9b.md>)

Recorded evaluation configuration: {"source":"(Zhang et al., 2020b)"}. This record does not assert independent reproduction.

### fastText

Accuracy: 92.81. Result ID: 698e0f3effc3901de09a7b01.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62a21e209131ce9fa626.md>)

[Implementation](<https://github.com/facebookresearch/fastText>)

Recorded evaluation configuration: {"source":"(Zhang et al., 2020b)"}. This record does not assert independent reproduction.

### TextRNN

Accuracy: 90.54. Result ID: 698e0f3effc3901de09a7b00.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa678e1e209131cea16f9b.md>)

Recorded evaluation configuration: {"source":"(Zhang et al., 2020b)"}. This record does not assert independent reproduction.

### TextCNN

Accuracy: 87.59. Result ID: 698e0f3effc3901de09a7aff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa678e1e209131cea16f9b.md>)

Recorded evaluation configuration: {"source":"(Zhang et al., 2020b)"}. This record does not assert independent reproduction.

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