# Ranking correlation with full dataset evaluation on QuaRel

Source: [Ranking correlation with full dataset evaluation on QuaRel](<https://www.sota2.com/research/sota/ranking-correlation-with-full-dataset-evaluation-on-quarel>)

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

Data updated: 2026-02-26T05:47:49.370Z

Evaluation of model ranking correlation performance using the QuaRel dataset, measured via Kendall correlation across the full dataset evaluation.

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 | Ranking correlation with full dataset evaluation |
| Dataset (including any stated split) | QuaRel |
| Metric | Kendall Correlation |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Kendall Correlation](<https://www.sota2.com/research/sota/ranking-correlation-with-full-dataset-evaluation-on-quarel.md?metric=Kendall%20Correlation>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Kendall Correlation | Result date | Report paper |
| --- | --- | --- | --- |
| ILDAE | 0.51 | Not recorded | 68fa6bf21e209131cea311ae |
| ILDAE | 0.39 | Not recorded | 68fa6bf21e209131cea311ae |
| ILDAE | 0.33 | Not recorded | 68fa6bf21e209131cea311ae |
| ILDAE | 0.32 | Not recorded | 68fa6bf21e209131cea311ae |

### ILDAE

Kendall Correlation: 0.51. Result ID: 698eacd9ffc3901de09faf6e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf21e209131cea311ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf21e209131cea311ae.md>)

[Implementation](<https://github.com/nrjvarshney/ILDAE>)

Recorded evaluation configuration: {"Percentage of instances":"20%"}. This record does not assert independent reproduction.

### ILDAE

Kendall Correlation: 0.39. Result ID: 698eacd9ffc3901de09faf6d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf21e209131cea311ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf21e209131cea311ae.md>)

[Implementation](<https://github.com/nrjvarshney/ILDAE>)

Recorded evaluation configuration: {"Percentage of instances":"10%"}. This record does not assert independent reproduction.

### ILDAE

Kendall Correlation: 0.33. Result ID: 698eacd9ffc3901de09faf6c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf21e209131cea311ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf21e209131cea311ae.md>)

[Implementation](<https://github.com/nrjvarshney/ILDAE>)

Recorded evaluation configuration: {"Percentage of instances":"5%"}. This record does not assert independent reproduction.

### ILDAE

Kendall Correlation: 0.32. Result ID: 698eacd9ffc3901de09faf6b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf21e209131cea311ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf21e209131cea311ae.md>)

[Implementation](<https://github.com/nrjvarshney/ILDAE>)

Recorded evaluation configuration: {"Percentage of instances":"2%"}. This record does not assert independent reproduction.

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