# Ranking on TREC DL Source: [Ranking on TREC DL]() Collection index: [llms.txt]() Data updated: 2026-04-14T07:00:28.698Z Evaluation of general ranking performance on the TREC DL dataset, measured using metrics such as NDCG. 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 | Ranking | | Dataset (including any stated split) | TREC DL | | Metric | NDCG@5 | | 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@5](): Higher is better; unit: PERCENT. ## Recorded results | Method | NDCG@5 | Result date | Report paper | | --- | --- | --- | --- | | ITEM-Ar | 83.12 | Not recorded | 68fa7aba1e209131cea84d8e | | ITEM-ARs | 82.89 | Not recorded | 68fa7aba1e209131cea84d8e | | ITEM-ARs | 81.38 | Not recorded | 68fa7aba1e209131cea84d8e | | ITEM-Ar | 80.79 | Not recorded | 68fa7aba1e209131cea84d8e | | RankGPT | 80.56 | Not recorded | 68fa7aba1e209131cea84d8e | | ITEM-Ar | 77.34 | Not recorded | 68fa7aba1e209131cea84d8e | | ITEM-ARs | 77.22 | Not recorded | 68fa7aba1e209131cea84d8e | | RankGPT | 75.61 | Not recorded | 68fa7aba1e209131cea84d8e | | ITEM-ARs | 74.8 | Not recorded | 68fa7aba1e209131cea84d8e | | ITEM-Ar | 74.27 | Not recorded | 68fa7aba1e209131cea84d8e | | ITEM-Ar | 73.95 | Not recorded | 68fa7aba1e209131cea84d8e | | ITEM-ARs | 73.24 | Not recorded | 68fa7aba1e209131cea84d8e | | ITEM-ARs | 71.29 | Not recorded | 68fa7aba1e209131cea84d8e | | ITEM-Ar | 70.57 | Not recorded | 68fa7aba1e209131cea84d8e | | RankGPT | 69.81 | Not recorded | 68fa7aba1e209131cea84d8e | | D | 58.69 | Not recorded | 68fa7aba1e209131cea84d8e | | D | 58.69 | Not recorded | 68fa7aba1e209131cea84d8e | | D | 58.69 | Not recorded | 68fa7aba1e209131cea84d8e | ### ITEM-Ar NDCG@5: 83.12. Result ID: 69dde4c647f34ce924c4c842. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"ChatGPT","Iterations":"3"}. This record does not assert independent reproduction. ### ITEM-ARs NDCG@5: 82.89. Result ID: 69dde4c647f34ce924c4c845. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"ChatGPT","Iterations":"3"}. This record does not assert independent reproduction. ### ITEM-ARs NDCG@5: 81.38. Result ID: 69dde4c647f34ce924c4c83f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"ChatGPT","Iterations":"1"}. This record does not assert independent reproduction. ### ITEM-Ar NDCG@5: 80.79. Result ID: 69dde4c647f34ce924c4c83c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"ChatGPT","Iterations":"1"}. This record does not assert independent reproduction. ### RankGPT NDCG@5: 80.56. Result ID: 69dde4c647f34ce924c4c839. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"ChatGPT"}. This record does not assert independent reproduction. ### ITEM-Ar NDCG@5: 77.34. Result ID: 69dde4c647f34ce924c4c841. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Llama 3","Iterations":"3"}. This record does not assert independent reproduction. ### ITEM-ARs NDCG@5: 77.22. Result ID: 69dde4c647f34ce924c4c83e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Llama 3","Iterations":"1"}. This record does not assert independent reproduction. ### RankGPT NDCG@5: 75.61. Result ID: 69dde4c647f34ce924c4c838. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Llama 3"}. This record does not assert independent reproduction. ### ITEM-ARs NDCG@5: 74.8. Result ID: 69dde4c647f34ce924c4c844. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Llama 3","Iterations":"3"}. This record does not assert independent reproduction. ### ITEM-Ar NDCG@5: 74.27. Result ID: 69dde4c647f34ce924c4c840. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Mistral","Iterations":"3"}. This record does not assert independent reproduction. ### ITEM-Ar NDCG@5: 73.95. Result ID: 69dde4c647f34ce924c4c83b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Llama 3","Iterations":"1"}. This record does not assert independent reproduction. ### ITEM-ARs NDCG@5: 73.24. Result ID: 69dde4c647f34ce924c4c843. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Mistral","Iterations":"3"}. This record does not assert independent reproduction. ### ITEM-ARs NDCG@5: 71.29. Result ID: 69dde4c647f34ce924c4c83d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Mistral","Iterations":"1"}. This record does not assert independent reproduction. ### ITEM-Ar NDCG@5: 70.57. Result ID: 69dde4c647f34ce924c4c83a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Mistral","Iterations":"1"}. This record does not assert independent reproduction. ### RankGPT NDCG@5: 69.81. Result ID: 69dde4c647f34ce924c4c837. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Mistral"}. This record does not assert independent reproduction. ### D NDCG@5: 58.69. Result ID: 69dde4c647f34ce924c4c834. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Mistral"}. This record does not assert independent reproduction. ### D NDCG@5: 58.69. Result ID: 69dde4c647f34ce924c4c835. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Llama 3"}. This record does not assert independent reproduction. ### D NDCG@5: 58.69. Result ID: 69dde4c647f34ce924c4c836. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"ChatGPT"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.