# Law-level retrieval on Austrian-law benchmark (test)

Source: [Law-level retrieval on Austrian-law benchmark (test)](<https://www.sota2.com/research/sota/law-level-retrieval-on-austrian-law-benchmark-test>)

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

Data updated: 2026-05-06T07:05:01.777Z

Evaluation of Law-level retrieval performance on the test split of the Austrian-law benchmark, measured using Mean lift (prior).

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 | Law-level retrieval |
| Dataset (including any stated split) | Austrian-law benchmark (test) |
| Metric | Mean Lift (Prior) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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 Lift (Prior)](<https://www.sota2.com/research/sota/law-level-retrieval-on-austrian-law-benchmark-test.md?metric=Mean%20Lift%20(Prior)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Mean Lift (Prior) | Result date | Report paper |
| --- | --- | --- | --- |
| KAHM | 67.163 | Not recorded | 69facae7c0f56ed84308a223 |
| KAHM | 62.404 | Not recorded | 69facae7c0f56ed84308a223 |
| Mixedbread | 60.549 | Not recorded | 69facae7c0f56ed84308a223 |
| Mixedbread | 57.062 | Not recorded | 69facae7c0f56ed84308a223 |
| KAHM | 55.824 | Not recorded | 69facae7c0f56ed84308a223 |
| KAHM | 50.812 | Not recorded | 69facae7c0f56ed84308a223 |
| Mixedbread | 49.011 | Not recorded | 69facae7c0f56ed84308a223 |
| KAHM | 47.025 | Not recorded | 69facae7c0f56ed84308a223 |
| Mixedbread | 44.308 | Not recorded | 69facae7c0f56ed84308a223 |
| IDF–SVD | 42.062 | Not recorded | 69facae7c0f56ed84308a223 |
| Mixedbread | 40.339 | Not recorded | 69facae7c0f56ed84308a223 |
| IDF–SVD | 38.9 | Not recorded | 69facae7c0f56ed84308a223 |
| IDF–SVD | 35.715 | Not recorded | 69facae7c0f56ed84308a223 |
| IDF–SVD | 33.889 | Not recorded | 69facae7c0f56ed84308a223 |
| IDF–SVD | 32.062 | Not recorded | 69facae7c0f56ed84308a223 |

### KAHM

Mean Lift (Prior): 67.163. Result ID: 69fae7bf47f34ce924dd51df.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"3"}. This record does not assert independent reproduction.

### KAHM

Mean Lift (Prior): 62.404. Result ID: 69fae7bf47f34ce924dd51e2.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction.

### Mixedbread

Mean Lift (Prior): 60.549. Result ID: 69fae7bf47f34ce924dd51e0.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"3"}. This record does not assert independent reproduction.

### Mixedbread

Mean Lift (Prior): 57.062. Result ID: 69fae7bf47f34ce924dd51e3.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction.

### KAHM

Mean Lift (Prior): 55.824. Result ID: 69fae7bf47f34ce924dd51e5.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"10"}. This record does not assert independent reproduction.

### KAHM

Mean Lift (Prior): 50.812. Result ID: 69fae7bf47f34ce924dd51e8.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"15"}. This record does not assert independent reproduction.

### Mixedbread

Mean Lift (Prior): 49.011. Result ID: 69fae7bf47f34ce924dd51e6.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"10"}. This record does not assert independent reproduction.

### KAHM

Mean Lift (Prior): 47.025. Result ID: 69fae7bf47f34ce924dd51eb.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"20"}. This record does not assert independent reproduction.

### Mixedbread

Mean Lift (Prior): 44.308. Result ID: 69fae7bf47f34ce924dd51e9.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"15"}. This record does not assert independent reproduction.

### IDF–SVD

Mean Lift (Prior): 42.062. Result ID: 69fae7bf47f34ce924dd51de.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"3"}. This record does not assert independent reproduction.

### Mixedbread

Mean Lift (Prior): 40.339. Result ID: 69fae7bf47f34ce924dd51ec.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"20"}. This record does not assert independent reproduction.

### IDF–SVD

Mean Lift (Prior): 38.9. Result ID: 69fae7bf47f34ce924dd51e1.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction.

### IDF–SVD

Mean Lift (Prior): 35.715. Result ID: 69fae7bf47f34ce924dd51e4.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"10"}. This record does not assert independent reproduction.

### IDF–SVD

Mean Lift (Prior): 33.889. Result ID: 69fae7bf47f34ce924dd51e7.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"15"}. This record does not assert independent reproduction.

### IDF–SVD

Mean Lift (Prior): 32.062. Result ID: 69fae7bf47f34ce924dd51ea.

[Reporting paper](<https://www.sota2.com/research/paper/69facae7c0f56ed84308a223.md>)

Recorded evaluation configuration: {"k":"20"}. This record does not assert independent reproduction.

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