# Legal Case Retrieval on LeCaRD v2

Source: [Legal Case Retrieval on LeCaRD v2](<https://www.sota2.com/research/sota/legal-case-retrieval-on-lecard-v2>)

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

Data updated: 2026-04-28T09:12:01.749Z

Evaluation of model performance on Legal Case Retrieval using the LeCaRD v2 dataset, measured by ranking metrics such as MAP, MRR, and Hits@K.

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 | Legal Case Retrieval |
| Dataset (including any stated split) | LeCaRD v2 |
| Metric | MAP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [MAP](<https://www.sota2.com/research/sota/legal-case-retrieval-on-lecard-v2.md?metric=MAP>): Higher is better; unit: PERCENT.

- [Precision@3](<https://www.sota2.com/research/sota/legal-case-retrieval-on-lecard-v2.md?metric=Precision%403>): Higher is better; unit: PERCENT.

- [Recall@3](<https://www.sota2.com/research/sota/legal-case-retrieval-on-lecard-v2.md?metric=Recall%403>): Higher is better; unit: PERCENT.

- [Recall@5](<https://www.sota2.com/research/sota/legal-case-retrieval-on-lecard-v2.md?metric=Recall%405>): Higher is better; unit: PERCENT.

- [Hits@3](<https://www.sota2.com/research/sota/legal-case-retrieval-on-lecard-v2.md?metric=Hits%403>): Higher is better; unit: PERCENT.

- [Hits@5](<https://www.sota2.com/research/sota/legal-case-retrieval-on-lecard-v2.md?metric=Hits%405>): Higher is better; unit: PERCENT.

- [MRR@5](<https://www.sota2.com/research/sota/legal-case-retrieval-on-lecard-v2.md?metric=MRR%405>): Higher is better; unit: PERCENT.

## Recorded results

| Method | MAP | Result date | Report paper |
| --- | --- | --- | --- |
| GLIER | 76.58 | Not recorded | 69f03f5455a3c32af89fa37c |
| KELLER | 76.22 | Not recorded | 69f03f5455a3c32af89fa37c |
| SAILER | 73.6 | Not recorded | 69f03f5455a3c32af89fa37c |
| Lawformer | 70.44 | Not recorded | 69f03f5455a3c32af89fa37c |
| BGE | 68.98 | Not recorded | 69f03f5455a3c32af89fa37c |
| RoBERTa | 66.84 | Not recorded | 69f03f5455a3c32af89fa37c |
| BERT | 65.71 | Not recorded | 69f03f5455a3c32af89fa37c |
| BM25 | 58.43 | Not recorded | 69f03f5455a3c32af89fa37c |

### GLIER

MAP: 76.58. Result ID: 69f079d247f34ce924d69c33.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5455a3c32af89fa37c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f5455a3c32af89fa37c.md>)

Recorded evaluation configuration: {"Category":"Legal-Specific Re-ranking Models"}. This record does not assert independent reproduction.

### KELLER

MAP: 76.22. Result ID: 69f079d247f34ce924d69c32.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5455a3c32af89fa37c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73db1e209131cea5e85d.md>)

Recorded evaluation configuration: {"Category":"Legal-Specific Re-ranking Models"}. This record does not assert independent reproduction.

### SAILER

MAP: 73.6. Result ID: 69f079d247f34ce924d69c31.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5455a3c32af89fa37c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f231e209131cea43f91.md>)

Recorded evaluation configuration: {"Category":"Legal-Specific Pre-trained Models"}. This record does not assert independent reproduction.

### Lawformer

MAP: 70.44. Result ID: 69f079d247f34ce924d69c30.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5455a3c32af89fa37c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69e61e209131cea24b8a.md>)

Recorded evaluation configuration: {"Category":"Legal-Specific Pre-trained Models"}. This record does not assert independent reproduction.

### BGE

MAP: 68.98. Result ID: 69f079d247f34ce924d69c2f.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5455a3c32af89fa37c.md>)

Recorded evaluation configuration: {"Category":"General Pre-trained Models"}. This record does not assert independent reproduction.

### RoBERTa

MAP: 66.84. Result ID: 69f079d247f34ce924d69c2e.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5455a3c32af89fa37c.md>)

Recorded evaluation configuration: {"Category":"General Pre-trained Models"}. This record does not assert independent reproduction.

### BERT

MAP: 65.71. Result ID: 69f079d247f34ce924d69c2d.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5455a3c32af89fa37c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Category":"General Pre-trained Models"}. This record does not assert independent reproduction.

### BM25

MAP: 58.43. Result ID: 69f079d247f34ce924d69c2c.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5455a3c32af89fa37c.md>)

Recorded evaluation configuration: {"Category":"Traditional Retrieval Models"}. This record does not assert independent reproduction.

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