# Document Retrieval on MS MARCO document retrieval (DL'20) Source: [Document Retrieval on MS MARCO document retrieval (DL'20)]() Collection index: [llms.txt]() Data updated: 2026-06-11T08:08:28.607Z Evaluation of Document Retrieval performance on the MS MARCO document retrieval (DL'20) track, measured using NDCG@10. 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 Retrieval | | Dataset (including any stated split) | MS MARCO document retrieval (DL'20) | | Metric | NDCG@10 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 25 of 25 | | 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@10](): Higher is better; unit: PERCENT. ## Recorded results | Method | NDCG@10 | Result date | Report paper | | --- | --- | --- | --- | | SPLADE-v2 | 72 | Not recorded | 6a28f37190966ade919c1930 | | STORM64 | 67.3 | Not recorded | 6a28f37190966ade919c1930 | | STORM64 | 64.4 | Not recorded | 6a28f37190966ade919c1930 | | LLaMA2-Llama2Vec | 63.6 | Not recorded | 68fa71ae1e209131cea52833 | | LLaMA2-RepLLaMA | 63.2 | Not recorded | 68fa71ae1e209131cea52833 | | MuGI | 61.7 | Not recorded | 6a28f37190966ade919c1930 | | QUESTER | 60.8 | Not recorded | 6a28f37190966ade919c1930 | | STORM32 | 60.2 | Not recorded | 6a28f37190966ade919c1930 | | W2P | 59.9 | Not recorded | 6a28f37190966ade919c1930 | | W2P | 58.8 | Not recorded | 6a28f37190966ade919c1930 | | MuGI | 58.8 | Not recorded | 6a28f37190966ade919c1930 | | MuGI | 57.8 | Not recorded | 6a28f37190966ade919c1930 | | STORM32 | 57.2 | Not recorded | 6a28f37190966ade919c1930 | | W2P | 56.1 | Not recorded | 6a28f37190966ade919c1930 | | QUESTER | 55.3 | Not recorded | 6a28f37190966ade919c1930 | | QUESTER | 54.8 | Not recorded | 6a28f37190966ade919c1930 | | MuGI | 54.8 | Not recorded | 6a28f37190966ade919c1930 | | BM25 | 52.9 | Not recorded | 68fa71ae1e209131cea52833 | | W2P | 51.1 | Not recorded | 6a28f37190966ade919c1930 | | RM3 | 49 | Not recorded | 6a28f37190966ade919c1930 | | BM25 | 48 | Not recorded | 6a28f37190966ade919c1930 | | HyDE | 41.7 | Not recorded | 6a28f37190966ade919c1930 | | HyDE | 40.7 | Not recorded | 6a28f37190966ade919c1930 | | HyDE | 34.9 | Not recorded | 6a28f37190966ade919c1930 | | HyDE | 25.6 | Not recorded | 6a28f37190966ade919c1930 | ### SPLADE-v2 NDCG@10: 72. Result ID: 6a2a6ce5fbc373592c276446. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Size":"None"}. This record does not assert independent reproduction. ### STORM64 NDCG@10: 67.3. Result ID: 6a2a6ce5fbc373592c27644a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Size":"8B"}. This record does not assert independent reproduction. ### STORM64 NDCG@10: 64.4. Result ID: 6a2a6ce5fbc373592c27644f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Size":"4B"}. This record does not assert independent reproduction. ### LLaMA2-Llama2Vec NDCG@10: 63.6. Result ID: 6991db6c3a6c3148490b0835. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B","Fine-tuning strategy":"hard"}. This record does not assert independent reproduction. ### LLaMA2-RepLLaMA NDCG@10: 63.2. Result ID: 6991db6c3a6c3148490b0834. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B","Fine-tuning strategy":"hard"}. This record does not assert independent reproduction. ### MuGI NDCG@10: 61.7. Result ID: 6a2a6ce5fbc373592c276448. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Size":"8B"}. This record does not assert independent reproduction. ### QUESTER NDCG@10: 60.8. Result ID: 6a2a6ce5fbc373592c27644e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Size":"4B"}. This record does not assert independent reproduction. ### STORM32 NDCG@10: 60.2. Result ID: 6a2a6ce5fbc373592c276454. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Size":"1.7B"}. This record does not assert independent reproduction. ### W2P NDCG@10: 59.9. Result ID: 6a2a6ce5fbc373592c276449. [Reporting paper]() Recorded evaluation configuration: {"Backbone Size":"8B"}. This record does not assert independent reproduction. ### W2P NDCG@10: 58.8. Result ID: 6a2a6ce5fbc373592c27644d. [Reporting paper]() Recorded evaluation configuration: {"Backbone Size":"4B"}. This record does not assert independent reproduction. ### MuGI NDCG@10: 58.8. Result ID: 6a2a6ce5fbc373592c276451. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Size":"1.7B"}. This record does not assert independent reproduction. ### MuGI NDCG@10: 57.8. Result ID: 6a2a6ce5fbc373592c27644c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Size":"4B"}. This record does not assert independent reproduction. ### STORM32 NDCG@10: 57.2. Result ID: 6a2a6ce5fbc373592c276459. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Size":"0.6B"}. This record does not assert independent reproduction. ### W2P NDCG@10: 56.1. Result ID: 6a2a6ce5fbc373592c276452. [Reporting paper]() Recorded evaluation configuration: {"Backbone Size":"1.7B"}. This record does not assert independent reproduction. ### QUESTER NDCG@10: 55.3. Result ID: 6a2a6ce5fbc373592c276458. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Size":"0.6B"}. This record does not assert independent reproduction. ### QUESTER NDCG@10: 54.8. Result ID: 6a2a6ce5fbc373592c276453. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Size":"1.7B"}. This record does not assert independent reproduction. ### MuGI NDCG@10: 54.8. Result ID: 6a2a6ce5fbc373592c276456. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Size":"0.6B"}. This record does not assert independent reproduction. ### BM25 NDCG@10: 52.9. Result ID: 6991db6c3a6c3148490b0833. [Reporting paper]() Recorded evaluation configuration: {"Size":null,"Fine-tuning strategy":null}. This record does not assert independent reproduction. ### W2P NDCG@10: 51.1. Result ID: 6a2a6ce5fbc373592c276457. [Reporting paper]() Recorded evaluation configuration: {"Backbone Size":"0.6B"}. This record does not assert independent reproduction. ### RM3 NDCG@10: 49. Result ID: 6a2a6ce5fbc373592c276445. [Reporting paper]() Recorded evaluation configuration: {"Backbone Size":"None"}. This record does not assert independent reproduction. ### BM25 NDCG@10: 48. Result ID: 6a2a6ce5fbc373592c276444. [Reporting paper]() Recorded evaluation configuration: {"Backbone Size":"None"}. This record does not assert independent reproduction. ### HyDE NDCG@10: 41.7. Result ID: 6a2a6ce5fbc373592c27644b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Size":"4B"}. This record does not assert independent reproduction. ### HyDE NDCG@10: 40.7. Result ID: 6a2a6ce5fbc373592c276447. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Size":"8B"}. This record does not assert independent reproduction. ### HyDE NDCG@10: 34.9. Result ID: 6a2a6ce5fbc373592c276450. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Size":"1.7B"}. This record does not assert independent reproduction. ### HyDE NDCG@10: 25.6. Result ID: 6a2a6ce5fbc373592c276455. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Size":"0.6B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.