# Nugget Coverage Reranking on CRUX-MDS DUC 2004 (test) Source: [Nugget Coverage Reranking on CRUX-MDS DUC 2004 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:11:07.969Z Evaluation of Nugget Coverage Reranking performance on the test split of the CRUX-MDS DUC 2004 dataset, measured using nDCG, Precision, alpha-nDCG, and Coverage. 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 | Nugget Coverage Reranking | | Dataset (including any stated split) | CRUX-MDS DUC 2004 (test) | | Metric | nDCG | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [nDCG](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. - [Alpha-nDCG](): Higher is better; unit: PERCENT. - [Coverage](): Higher is better; unit: PERCENT. ## Recorded results | Method | nDCG | Result date | Report paper | | --- | --- | --- | --- | | LANCER\_Q\* | 88.2 | Not recorded | 697c3b75a8b01e76cc8da79c | | LANCER\_Q\* | 86.3 | Not recorded | 697c3b75a8b01e76cc8da79c | | Pointwise | 83.9 | Not recorded | 697c3b75a8b01e76cc8da79c | | Pointwise | 83.1 | Not recorded | 697c3b75a8b01e76cc8da79c | | Listwise | 81.7 | Not recorded | 697c3b75a8b01e76cc8da79c | | LANCER | 80.8 | Not recorded | 697c3b75a8b01e76cc8da79c | | Listwise | 80.6 | Not recorded | 697c3b75a8b01e76cc8da79c | | LANCER\_Q\* | 80.3 | Not recorded | 697c3b75a8b01e76cc8da79c | | LANCER | 78.9 | Not recorded | 697c3b75a8b01e76cc8da79c | | Listwise | 77.1 | Not recorded | 697c3b75a8b01e76cc8da79c | | Pointwise | 76.1 | Not recorded | 697c3b75a8b01e76cc8da79c | | Qwen3-Embed | 75.9 | Not recorded | 697c3b75a8b01e76cc8da79c | | Setwise | 75.3 | Not recorded | 697c3b75a8b01e76cc8da79c | | LANCER | 73.8 | Not recorded | 697c3b75a8b01e76cc8da79c | | Setwise | 71.3 | Not recorded | 697c3b75a8b01e76cc8da79c | | LSR | 70.4 | Not recorded | 697c3b75a8b01e76cc8da79c | | Setwise | 69.2 | Not recorded | 697c3b75a8b01e76cc8da79c | | BM25 | 53 | Not recorded | 697c3b75a8b01e76cc8da79c | ### LANCER\_Q\* nDCG: 88.2. Result ID: 6998a7ef5698665ec40a97fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"Qwen3-Embed","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### LANCER\_Q\* nDCG: 86.3. Result ID: 6998a7ef5698665ec40a97f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"LSR","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### Pointwise nDCG: 83.9. Result ID: 6998a7ef5698665ec40a97f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"Qwen3-Embed","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### Pointwise nDCG: 83.1. Result ID: 6998a7ef5698665ec40a97f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"LSR","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### Listwise nDCG: 81.7. Result ID: 6998a7ef5698665ec40a97fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"Qwen3-Embed","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### LANCER nDCG: 80.8. Result ID: 6998a7ef5698665ec40a97fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"Qwen3-Embed","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### Listwise nDCG: 80.6. Result ID: 6998a7ef5698665ec40a97f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"LSR","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### LANCER\_Q\* nDCG: 80.3. Result ID: 6998a7ef5698665ec40a97f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"BM25","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### LANCER nDCG: 78.9. Result ID: 6998a7ef5698665ec40a97f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"LSR","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### Listwise nDCG: 77.1. Result ID: 6998a7ef5698665ec40a97ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"BM25","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### Pointwise nDCG: 76.1. Result ID: 6998a7ef5698665ec40a97ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"BM25","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### Qwen3-Embed nDCG: 75.9. Result ID: 6998a7ef5698665ec40a97f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"type":"First-stage retrieval"}. This record does not assert independent reproduction. ### Setwise nDCG: 75.3. Result ID: 6998a7ef5698665ec40a97fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"Qwen3-Embed","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### LANCER nDCG: 73.8. Result ID: 6998a7ef5698665ec40a97f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"BM25","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### Setwise nDCG: 71.3. Result ID: 6998a7ef5698665ec40a97f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"LSR","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### LSR nDCG: 70.4. Result ID: 6998a7ef5698665ec40a97f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"type":"First-stage retrieval"}. This record does not assert independent reproduction. ### Setwise nDCG: 69.2. Result ID: 6998a7ef5698665ec40a97ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"First-stage retrieval":"BM25","LLM Backbone":"Llama-3.3-70B-Instruct"}. This record does not assert independent reproduction. ### BM25 nDCG: 53. Result ID: 6998a7ef5698665ec40a97ec. [Reporting paper]() Recorded evaluation configuration: {"type":"First-stage retrieval"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.