# Toxicity Classification on Toxicity Dataset (test)

Source: [Toxicity Classification on Toxicity Dataset (test)](<https://www.sota2.com/research/sota/toxicity-classification-on-toxicity-dataset-test>)

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

Data updated: 2026-04-08T09:12:16.919Z

Evaluation of model performance on the test split of the Toxicity Dataset for the task of Toxicity Classification, reporting Test Accuracy, Macro F1, and Minimum 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 | Toxicity Classification |
| Dataset (including any stated split) | Toxicity Dataset (test) |
| Metric | Test Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Test Accuracy](<https://www.sota2.com/research/sota/toxicity-classification-on-toxicity-dataset-test.md?metric=Test%20Accuracy>): Higher is better; unit: PERCENT.

- [Macro F1](<https://www.sota2.com/research/sota/toxicity-classification-on-toxicity-dataset-test.md?metric=Macro%20F1>): Higher is better; unit: PERCENT.

- [Minimum F1](<https://www.sota2.com/research/sota/toxicity-classification-on-toxicity-dataset-test.md?metric=Minimum%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Test Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CoGate-LSTM | 96 | Not recorded | 68fa7c571e209131cea8da9a |
| BERT + weighted loss | 95.54 | Not recorded | 68fa7c571e209131cea8da9a |
| LSTM + weighted loss | 95.21 | Not recorded | 68fa7c571e209131cea8da9a |
| Ensemble (most-conf.) | 95.14 | Not recorded | 68fa7c571e209131cea8da9a |
| XGBoost | 94.37 | Not recorded | 68fa7c571e209131cea8da9a |
| Logistic Regression | 93.64 | Not recorded | 68fa7c571e209131cea8da9a |
| Linear SVM (SGD) | 93.16 | Not recorded | 68fa7c571e209131cea8da9a |
| Naive Bayes SVM | 87.57 | Not recorded | 68fa7c571e209131cea8da9a |
| Random Forest | 76.85 | Not recorded | 68fa7c571e209131cea8da9a |

### CoGate-LSTM

Test Accuracy: 96. Result ID: 69d61bdf47f34ce924bee54d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

Recorded evaluation configuration: {"Family":"Deep"}. This record does not assert independent reproduction.

### BERT + weighted loss

Test Accuracy: 95.54. Result ID: 69d61bdf47f34ce924bee54b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Family":"Deep"}. This record does not assert independent reproduction.

### LSTM + weighted loss

Test Accuracy: 95.21. Result ID: 69d61bdf47f34ce924bee54a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

Recorded evaluation configuration: {"Family":"Deep"}. This record does not assert independent reproduction.

### Ensemble (most-conf.)

Test Accuracy: 95.14. Result ID: 69d61bdf47f34ce924bee54c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

Recorded evaluation configuration: {"Family":"Deep"}. This record does not assert independent reproduction.

### XGBoost

Test Accuracy: 94.37. Result ID: 69d61bdf47f34ce924bee549.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d61e209131cea247ea.md>)

Recorded evaluation configuration: {"Family":"Ensemble"}. This record does not assert independent reproduction.

### Logistic Regression

Test Accuracy: 93.64. Result ID: 69d61bdf47f34ce924bee546.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f291e209131cea44261.md>)

Recorded evaluation configuration: {"Family":"Classical"}. This record does not assert independent reproduction.

### Linear SVM (SGD)

Test Accuracy: 93.16. Result ID: 69d61bdf47f34ce924bee547.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

Recorded evaluation configuration: {"Family":"Classical"}. This record does not assert independent reproduction.

### Naive Bayes SVM

Test Accuracy: 87.57. Result ID: 69d61bdf47f34ce924bee545.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa684f1e209131cea1b533.md>)

Recorded evaluation configuration: {"Family":"Baseline"}. This record does not assert independent reproduction.

### Random Forest

Test Accuracy: 76.85. Result ID: 69d61bdf47f34ce924bee548.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d61e209131cea247ea.md>)

Recorded evaluation configuration: {"Family":"Ensemble"}. This record does not assert independent reproduction.

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