# Commonsense Question Answering on CQA (test)

Source: [Commonsense Question Answering on CQA (test)](<https://www.sota2.com/research/sota/commonsense-question-answering-on-cqa-test>)

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

Data updated: 2026-02-26T05:29:43.158Z

Evaluation of model performance on the test split of the CQA dataset for Commonsense Question Answering, measured by 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 | Commonsense Question Answering |
| Dataset (including any stated split) | CQA (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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/commonsense-question-answering-on-cqa-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MI-based distillation | 43.9 | Not recorded | 68fa73861e209131cea5cefb |
| DSS | 43.24 | Not recorded | 68fa73861e209131cea5cefb |
| Finetuning | 43.16 | Not recorded | 68fa73861e209131cea5cefb |

### MI-based distillation

Accuracy: 43.9. Result ID: 6992e69a3a6c314849123efb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cefb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cefb.md>)

[Implementation](<https://github.com/xinchen9/cot_distillation_ACL2024>)

Recorded evaluation configuration: {"Backbone":"T5-small"}. This record does not assert independent reproduction.

### DSS

Accuracy: 43.24. Result ID: 6992e69a3a6c314849123efa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cefb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70001e209131cea4871e.md>)

Recorded evaluation configuration: {"Backbone":"T5-small","Evaluation Protocol":"Distilling Step-by-Step"}. This record does not assert independent reproduction.

### Finetuning

Accuracy: 43.16. Result ID: 6992e69a3a6c314849123ef9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cefb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64601e209131cea04261.md>)

[Implementation](<http://nlp.fast.ai/ulmfit>)

Recorded evaluation configuration: {"Backbone":"T5-small","Evaluation Protocol":"Standard Label Supervision"}. This record does not assert independent reproduction.

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