# Document Reranking on NQ (test) Source: [Document Reranking on NQ (test)]() Collection index: [llms.txt]() Data updated: 2026-05-07T08:27:49.920Z Evaluation of Document Reranking performance on the test split of the NQ dataset, measured using NDCG@5 and Δ%. 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 | Document Reranking | | Dataset (including any stated split) | NQ (test) | | Metric | NDCG@5 | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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@5](): Higher is better; unit: SCALAR. - [Delta (%)](): Higher is better; unit: PERCENT. ## Recorded results | Method | NDCG@5 | Result date | Report paper | | --- | --- | --- | --- | | RankT5 | 8.339 | Not recorded | 69fc1cac5497b3b670c88615 | | RankT5 | 8.312 | Not recorded | 69fc1cac5497b3b670c88615 | | Cross-Encoder | 8.158 | Not recorded | 69fc1cac5497b3b670c88615 | | Cross-Encoder | 8.117 | Not recorded | 69fc1cac5497b3b670c88615 | | ColBERT | 7.994 | Not recorded | 69fc1cac5497b3b670c88615 | | ColBERT | 7.913 | Not recorded | 69fc1cac5497b3b670c88615 | | QLM | 6.292 | Not recorded | 69fc1cac5497b3b670c88615 | | QLM | 6.104 | Not recorded | 69fc1cac5497b3b670c88615 | | RankGPT | 5.486 | Not recorded | 69fc1cac5497b3b670c88615 | | BM25 | 5.478 | Not recorded | 69fc1cac5497b3b670c88615 | | RankGPT | 4.888 | Not recorded | 69fc1cac5497b3b670c88615 | | BM25 | 4.877 | Not recorded | 69fc1cac5497b3b670c88615 | | YesNo | 4.602 | Not recorded | 69fc1cac5497b3b670c88615 | | YesNo | 3.215 | Not recorded | 69fc1cac5497b3b670c88615 | ### RankT5 NDCG@5: 8.339. Result ID: 69fc4cf947f34ce924deff89. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"true","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. ### RankT5 NDCG@5: 8.312. Result ID: 69fc4cf947f34ce924deff88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"false","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. ### Cross-Encoder NDCG@5: 8.158. Result ID: 69fc4cf947f34ce924deff87. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"true","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. ### Cross-Encoder NDCG@5: 8.117. Result ID: 69fc4cf947f34ce924deff86. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"false","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. ### ColBERT NDCG@5: 7.994. Result ID: 69fc4cf947f34ce924deff85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"true","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. ### ColBERT NDCG@5: 7.913. Result ID: 69fc4cf947f34ce924deff84. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"false","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. ### QLM NDCG@5: 6.292. Result ID: 69fc4cf947f34ce924deff81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"true","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. ### QLM NDCG@5: 6.104. Result ID: 69fc4cf947f34ce924deff80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"false","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. ### RankGPT NDCG@5: 5.486. Result ID: 69fc4cf947f34ce924deff83. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"true","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. ### BM25 NDCG@5: 5.478. Result ID: 69fc4cf947f34ce924deff7d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"true","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. ### RankGPT NDCG@5: 4.888. Result ID: 69fc4cf947f34ce924deff82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"false","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. ### BM25 NDCG@5: 4.877. Result ID: 69fc4cf947f34ce924deff7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"false","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. ### YesNo NDCG@5: 4.602. Result ID: 69fc4cf947f34ce924deff7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"true","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. ### YesNo NDCG@5: 3.215. Result ID: 69fc4cf947f34ce924deff7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"CAR":"false","Generator":"Qwen2.5-7B-Instruct","Initial Retriever":"BM25"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.