# Ranking Preservation on tau-bench Airline (test)

Source: [Ranking Preservation on tau-bench Airline (test)](<https://www.sota2.com/research/sota/ranking-preservation-on-tau-bench-airline-test>)

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

Data updated: 2026-03-26T13:37:25.414Z

Evaluation of model performance on preserving ranking order within the tau-bench Airline dataset (test split), measured using Spearman correlation coefficients (mean, std, worst, best).

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 Preservation |
| Dataset (including any stated split) | tau-bench Airline (test) |
| Metric | Mean Spearman Rho |
| 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

- [Mean Spearman Rho](<https://www.sota2.com/research/sota/ranking-preservation-on-tau-bench-airline-test.md?metric=Mean%20Spearman%20Rho>): Higher is better; unit: SCALAR.

- [Std Dev Spearman Rho](<https://www.sota2.com/research/sota/ranking-preservation-on-tau-bench-airline-test.md?metric=Std%20Dev%20Spearman%20Rho>): Lower is better; unit: SCALAR.

- [Worst Spearman Rho](<https://www.sota2.com/research/sota/ranking-preservation-on-tau-bench-airline-test.md?metric=Worst%20Spearman%20Rho>): Higher is better; unit: SCALAR.

- [Best Spearman Rho](<https://www.sota2.com/research/sota/ranking-preservation-on-tau-bench-airline-test.md?metric=Best%20Spearman%20Rho>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Mean Spearman Rho | Result date | Report paper |
| --- | --- | --- | --- |
| MR | 0.944 | Not recorded | 69c4bd730636e5bf4afc74ed |
| Easiest | 0.92 | Not recorded | 69c4bd730636e5bf4afc74ed |
| Stratified | 0.874 | Not recorded | 69c4bd730636e5bf4afc74ed |
| Random | 0.86 | Not recorded | 69c4bd730636e5bf4afc74ed |
| Greedy | 0.834 | Not recorded | 69c4bd730636e5bf4afc74ed |

### MR

Mean Spearman Rho: 0.944. Result ID: 69c5366147f34ce924aed2a7.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd730636e5bf4afc74ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c4bd730636e5bf4afc74ed.md>)

Recorded evaluation configuration: {"k":"27","Selection strategy":"Mid-Range","Evaluation protocol":"mean across all protocols"}. This record does not assert independent reproduction.

### Easiest

Mean Spearman Rho: 0.92. Result ID: 69c5366147f34ce924aed2a9.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd730636e5bf4afc74ed.md>)

Recorded evaluation configuration: {"k":"27","Selection strategy":"Easiest","Evaluation protocol":"mean across all protocols"}. This record does not assert independent reproduction.

### Stratified

Mean Spearman Rho: 0.874. Result ID: 69c5366147f34ce924aed2aa.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd730636e5bf4afc74ed.md>)

Recorded evaluation configuration: {"k":"27","Selection strategy":"Stratified","Evaluation protocol":"mean across all protocols"}. This record does not assert independent reproduction.

### Random

Mean Spearman Rho: 0.86. Result ID: 69c5366147f34ce924aed2ab.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd730636e5bf4afc74ed.md>)

Recorded evaluation configuration: {"k":"27","Selection strategy":"Random","Evaluation protocol":"mean across all protocols"}. This record does not assert independent reproduction.

### Greedy

Mean Spearman Rho: 0.834. Result ID: 69c5366147f34ce924aed2a8.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd730636e5bf4afc74ed.md>)

Recorded evaluation configuration: {"k":"27","Selection strategy":"Greedy","Evaluation protocol":"mean across all protocols"}. This record does not assert independent reproduction.

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