# Legal Case Retrieval on COLIEE 2023 Source: [Legal Case Retrieval on COLIEE 2023]() Collection index: [llms.txt]() Data updated: 2026-03-06T06:58:15.279Z Evaluation of Legal Case Retrieval performance on the COLIEE 2023 dataset, utilizing standard ranking metrics (P@5, R@5, MRR, MAP, NDCG) and F1 scores. 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) | COLIEE 2023 | | Metric | P@5 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 - [P@5](): Higher is better; unit: PERCENT. - [R@5](): Higher is better; unit: PERCENT. - [Micro F1 Score](): Higher is better; unit: PERCENT. - [Macro F1 Score](): Higher is better; unit: PERCENT. - [MRR@5](): Higher is better; unit: PERCENT. - [MAP](): Higher is better; unit: PERCENT. - [NDCG@5](): Higher is better; unit: PERCENT. ## Recorded results | Method | P@5 | Result date | Report paper | | --- | --- | --- | --- | | LEXA | 22.6 | Not recorded | 68fa73491e209131cea5b8f6 | | PromptCase | 21.8 | Not recorded | 68fa73491e209131cea5b8f6 | | LEXA | 21.3 | Not recorded | 68fa73491e209131cea5b8f6 | | CaseLink | 21 | Not recorded | 68fa73491e209131cea5b8f6 | | CaseLink | 20.9 | Not recorded | 68fa73491e209131cea5b8f6 | | CaseGNN | 20.2 | Not recorded | 68fa73491e209131cea5b8f6 | | Qwen3-Embedding-8B | 20.1 | Not recorded | 68fa73491e209131cea5b8f6 | | E5-Mistral-7b-Instruct | 19.7 | Not recorded | 68fa73491e209131cea5b8f6 | | Inf-Retriever-V1 | 19.7 | Not recorded | 68fa73491e209131cea5b8f6 | | SAILER | 19.6 | Not recorded | 68fa73491e209131cea5b8f6 | | Inf-Retriever-V1 | 19 | Not recorded | 68fa73491e209131cea5b8f6 | | Qwen3-Embedding-8B | 18.4 | Not recorded | 68fa73491e209131cea5b8f6 | | CaseGNN | 17.7 | Not recorded | 68fa73491e209131cea5b8f6 | | BM25 | 16.5 | Not recorded | 68fa73491e209131cea5b8f6 | | PromptCase | 16 | Not recorded | 68fa73491e209131cea5b8f6 | | E5-Mistral-7b-Instruct | 16 | Not recorded | 68fa73491e209131cea5b8f6 | | SAILER | 12.8 | Not recorded | 68fa73491e209131cea5b8f6 | | LEGAL-BERT | 4.64 | Not recorded | 68fa73491e209131cea5b8f6 | | MonoT5 | 0.38 | Not recorded | 68fa73491e209131cea5b8f6 | ### LEXA P@5: 22.6. Result ID: 69aa7a576dbb7075b953a8ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage":"One-stage","Category":"Graph"}. This record does not assert independent reproduction. ### PromptCase P@5: 21.8. Result ID: 69aa7a576dbb7075b953a8af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage":"Two-stage","Category":"LM"}. This record does not assert independent reproduction. ### LEXA P@5: 21.3. Result ID: 69aa7a576dbb7075b953a8b5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage":"Two-stage","Category":"Graph"}. This record does not assert independent reproduction. ### CaseLink P@5: 21. Result ID: 69aa7a576dbb7075b953a8b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage":"Two-stage","Category":"Graph"}. This record does not assert independent reproduction. ### CaseLink P@5: 20.9. Result ID: 69aa7a576dbb7075b953a8ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage":"One-stage","Category":"Graph"}. This record does not assert independent reproduction. ### CaseGNN P@5: 20.2. Result ID: 69aa7a576dbb7075b953a8b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage":"Two-stage","Category":"Graph"}. This record does not assert independent reproduction. ### Qwen3-Embedding-8B P@5: 20.1. Result ID: 69aa7a576dbb7075b953a8b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage":"Two-stage","Category":"LLM"}. This record does not assert independent reproduction. ### E5-Mistral-7b-Instruct P@5: 19.7. Result ID: 69aa7a576dbb7075b953a8b0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Stage":"Two-stage","Category":"LLM"}. This record does not assert independent reproduction. ### Inf-Retriever-V1 P@5: 19.7. Result ID: 69aa7a576dbb7075b953a8b2. [Reporting paper]() Recorded evaluation configuration: {"Stage":"Two-stage","Category":"LLM"}. This record does not assert independent reproduction. ### SAILER P@5: 19.6. Result ID: 69aa7a576dbb7075b953a8ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage":"Two-stage","Category":"LM"}. This record does not assert independent reproduction. ### Inf-Retriever-V1 P@5: 19. Result ID: 69aa7a576dbb7075b953a8aa. [Reporting paper]() Recorded evaluation configuration: {"Stage":"One-stage","Category":"LLM"}. This record does not assert independent reproduction. ### Qwen3-Embedding-8B P@5: 18.4. Result ID: 69aa7a576dbb7075b953a8a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage":"One-stage","Category":"LLM"}. This record does not assert independent reproduction. ### CaseGNN P@5: 17.7. Result ID: 69aa7a576dbb7075b953a8ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage":"One-stage","Category":"Graph"}. This record does not assert independent reproduction. ### BM25 P@5: 16.5. Result ID: 69aa7a576dbb7075b953a8a3. [Reporting paper]() Recorded evaluation configuration: {"Stage":"One-stage"}. This record does not assert independent reproduction. ### PromptCase P@5: 16. Result ID: 69aa7a576dbb7075b953a8a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage":"One-stage","Category":"LM"}. This record does not assert independent reproduction. ### E5-Mistral-7b-Instruct P@5: 16. Result ID: 69aa7a576dbb7075b953a8a8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Stage":"One-stage","Category":"LLM"}. This record does not assert independent reproduction. ### SAILER P@5: 12.8. Result ID: 69aa7a576dbb7075b953a8a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage":"One-stage","Category":"LM"}. This record does not assert independent reproduction. ### LEGAL-BERT P@5: 4.64. Result ID: 69aa7a576dbb7075b953a8a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage":"One-stage","Category":"LM"}. This record does not assert independent reproduction. ### MonoT5 P@5: 0.38. Result ID: 69aa7a576dbb7075b953a8a5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Stage":"One-stage","Category":"LM"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.