# Information Retrieval on MS MARCO BEIR Source: [Information Retrieval on MS MARCO BEIR]() Collection index: [llms.txt]() Data updated: 2026-03-20T09:45:08.573Z Evaluation of Information Retrieval performance on the MS MARCO dataset configured under the BEIR evaluation framework, measured by metrics such as 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 | Information Retrieval | | Dataset (including any stated split) | MS MARCO BEIR | | Metric | NDCG@10 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 | | --- | --- | --- | --- | | LENS-d4K | 47 | Not recorded | 68fa7bc41e209131cea8a4c0 | | bge-en-icl | 46.8 | Not recorded | 68fa7bc41e209131cea8a4c0 | | inf-v1 | 44.1 | Not recorded | 68fa7bc41e209131cea8a4c0 | | Splade-V3 | 44 | Not recorded | 68fa7bc41e209131cea8a4c0 | | e5-large | 43.7 | Not recorded | 68fa7bc41e209131cea8a4c0 | | Qwen3-8B | 43.6 | Not recorded | 68fa7bc41e209131cea8a4c0 | | Qwen3-4B | 42.7 | Not recorded | 68fa7bc41e209131cea8a4c0 | | bge-large | 42.6 | Not recorded | 68fa7bc41e209131cea8a4c0 | | gte-base-v1.5 | 42.6 | Not recorded | 68fa7bc41e209131cea8a4c0 | | opensearch-gte | 42.6 | Not recorded | 68fa7bc41e209131cea8a4c0 | | bge-lg-v1.5 | 42.5 | Not recorded | 68fa7bc41e209131cea8a4c0 | | MILCO | 42 | Not recorded | 68fa7bc41e209131cea8a4c0 | | inf-v1-1.5b | 41 | Not recorded | 68fa7bc41e209131cea8a4c0 | | gte-large | 40.9 | Not recorded | 68fa7bc41e209131cea8a4c0 | | e5-large-inst | 40.4 | Not recorded | 68fa7bc41e209131cea8a4c0 | | gte-base | 40.2 | Not recorded | 68fa7bc41e209131cea8a4c0 | | Qwen3-0.6B | 38 | Not recorded | 68fa7bc41e209131cea8a4c0 | ### LENS-d4K NDCG@10: 47. Result ID: 69bd171147f34ce924a794d4. [Reporting paper]() Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction. ### bge-en-icl NDCG@10: 46.8. Result ID: 69bd171147f34ce924a794cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction. ### inf-v1 NDCG@10: 44.1. Result ID: 69bd171147f34ce924a794d5. [Reporting paper]() Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction. ### Splade-V3 NDCG@10: 44. Result ID: 69bd171147f34ce924a794dd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction. ### e5-large NDCG@10: 43.7. Result ID: 69bd171147f34ce924a794d9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction. ### Qwen3-8B NDCG@10: 43.6. Result ID: 69bd171147f34ce924a794ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction. ### Qwen3-4B NDCG@10: 42.7. Result ID: 69bd171147f34ce924a794d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction. ### bge-large NDCG@10: 42.6. Result ID: 69bd171147f34ce924a794d7. [Reporting paper]() Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction. ### gte-base-v1.5 NDCG@10: 42.6. Result ID: 69bd171147f34ce924a794d8. [Reporting paper]() Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction. ### opensearch-gte NDCG@10: 42.6. Result ID: 69bd171147f34ce924a794dc. [Reporting paper]() Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction. ### bge-lg-v1.5 NDCG@10: 42.5. Result ID: 69bd171147f34ce924a794da. [Reporting paper]() Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction. ### MILCO NDCG@10: 42. Result ID: 69bd171147f34ce924a794de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction. ### inf-v1-1.5b NDCG@10: 41. Result ID: 69bd171147f34ce924a794d1. [Reporting paper]() Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction. ### gte-large NDCG@10: 40.9. Result ID: 69bd171147f34ce924a794d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction. ### e5-large-inst NDCG@10: 40.4. Result ID: 69bd171147f34ce924a794d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction. ### gte-base NDCG@10: 40.2. Result ID: 69bd171147f34ce924a794d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction. ### Qwen3-0.6B NDCG@10: 38. Result ID: 69bd171147f34ce924a794db. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.