# Distractor Generation on CLOTH (test)

Source: [Distractor Generation on CLOTH (test)](<https://www.sota2.com/research/sota/distractor-generation-on-cloth-test>)

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

Data updated: 2026-05-20T08:23:58.888Z

Evaluation of Distractor Generation performance on the test split of the CLOTH dataset.

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 | Distractor Generation |
| Dataset (including any stated split) | CLOTH (test) |
| Metric | Invalid Ratio (Easy) |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 13 of 13 |
| 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

- [Invalid Ratio (Easy)](<https://www.sota2.com/research/sota/distractor-generation-on-cloth-test.md?metric=Invalid%20Ratio%20(Easy)>): Lower is better; unit: PERCENT.

- [Invalid Ratio](<https://www.sota2.com/research/sota/distractor-generation-on-cloth-test.md?metric=Invalid%20Ratio>): Lower is better; unit: PERCENT.

- [Chosen Ratio](<https://www.sota2.com/research/sota/distractor-generation-on-cloth-test.md?metric=Chosen%20Ratio>): Higher is better; unit: PERCENT.

- [Invalid Ratio (Hard)](<https://www.sota2.com/research/sota/distractor-generation-on-cloth-test.md?metric=Invalid%20Ratio%20(Hard)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Invalid Ratio (Easy) | Result date | Report paper |
| --- | --- | --- | --- |
| DCDG | 0.1 | Not recorded | 690988873ef7ccd74e5e5cab |
| DCDG | 0.2 | Not recorded | 690988873ef7ccd74e5e5cab |
| DCDG | 0.5 | Not recorded | 690988873ef7ccd74e5e5cab |
| DCDG | 0.9 | Not recorded | 690988873ef7ccd74e5e5cab |
| GPT-4o | 1.6 | Not recorded | 690988873ef7ccd74e5e5cab |
| GPT-4o | 6.8 | Not recorded | 690988873ef7ccd74e5e5cab |

### DCDG

Invalid Ratio (Easy): 0.1. Result ID: 6a0d6f97fbc373592c056bc7.

[Reporting paper](<https://www.sota2.com/research/paper/690988873ef7ccd74e5e5cab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988873ef7ccd74e5e5cab.md>)

Recorded evaluation configuration: {"ASDE":"true"}. This record does not assert independent reproduction.

### DCDG

Invalid Ratio (Easy): 0.2. Result ID: 6a0d6f97fbc373592c056bc9.

[Reporting paper](<https://www.sota2.com/research/paper/690988873ef7ccd74e5e5cab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988873ef7ccd74e5e5cab.md>)

Recorded evaluation configuration: {"ASDE":"true","DDDE":"true"}. This record does not assert independent reproduction.

### DCDG

Invalid Ratio (Easy): 0.5. Result ID: 6a0d6f97fbc373592c056bc8.

[Reporting paper](<https://www.sota2.com/research/paper/690988873ef7ccd74e5e5cab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988873ef7ccd74e5e5cab.md>)

Recorded evaluation configuration: {"DDDE":"true"}. This record does not assert independent reproduction.

### DCDG

Invalid Ratio (Easy): 0.9. Result ID: 6a0d6f97fbc373592c056bc6.

[Reporting paper](<https://www.sota2.com/research/paper/690988873ef7ccd74e5e5cab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988873ef7ccd74e5e5cab.md>)

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

### GPT-4o

Invalid Ratio (Easy): 1.6. Result ID: 6a0d6f97fbc373592c056bc5.

[Reporting paper](<https://www.sota2.com/research/paper/690988873ef7ccd74e5e5cab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"prompt\_mode":"5-shot"}. This record does not assert independent reproduction.

### GPT-4o

Invalid Ratio (Easy): 6.8. Result ID: 6a0d6f97fbc373592c056bc4.

[Reporting paper](<https://www.sota2.com/research/paper/690988873ef7ccd74e5e5cab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"prompt\_mode":"0-shot"}. This record does not assert independent reproduction.

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