# Distractor Generation on MCQ dataset

Source: [Distractor Generation on MCQ dataset](<https://www.sota2.com/research/sota/distractor-generation-on-mcq-dataset>)

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

Data updated: 2026-02-26T06:02:03.382Z

Evaluation of model performance on generating distractors for multiple-choice questions using the MCQ dataset, measured by Relevance, Distractiveness, and Utility.

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) | MCQ dataset |
| Metric | Relevance |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Relevance](<https://www.sota2.com/research/sota/distractor-generation-on-mcq-dataset.md?metric=Relevance>): Higher is better; unit: SCALAR.

- [Distractiveness](<https://www.sota2.com/research/sota/distractor-generation-on-mcq-dataset.md?metric=Distractiveness>): Higher is better; unit: SCALAR.

- [Utility](<https://www.sota2.com/research/sota/distractor-generation-on-mcq-dataset.md?metric=Utility>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Relevance | Result date | Report paper |
| --- | --- | --- | --- |
| RAP-T5 | 4.45 | Not recorded | 68fa73be1e209131cea5e347 |
| KAG | 4.05 | Not recorded | 68fa73be1e209131cea5e347 |
| Wang et al. | 3.81 | Not recorded | 68fa73be1e209131cea5e347 |
| ground truth | 3.52 | Not recorded | 68fa73be1e209131cea5e347 |
| ChatGPT | 3.14 | Not recorded | 68fa73be1e209131cea5e347 |

### RAP-T5

Relevance: 4.45. Result ID: 69931b233a6c31484913c3a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73be1e209131cea5e347.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73be1e209131cea5e347.md>)

Recorded evaluation configuration: {"Mode":"Text2text"}. This record does not assert independent reproduction.

### KAG

Relevance: 4.05. Result ID: 69931b233a6c31484913c39f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73be1e209131cea5e347.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73be1e209131cea5e347.md>)

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

### Wang et al.

Relevance: 3.81. Result ID: 69931b233a6c31484913c39e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73be1e209131cea5e347.md>)

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

### ground truth

Relevance: 3.52. Result ID: 69931b233a6c31484913c3a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73be1e209131cea5e347.md>)

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

### ChatGPT

Relevance: 3.14. Result ID: 69931b233a6c31484913c3a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73be1e209131cea5e347.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.