| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Passage Retrieval | MSMARCO (dev) | MRR@1042.6 | 116 | |
| Document Retrieval | MSMarco (dev) | NDCG@1043.2 | 41 | |
| Generative Question Answering | MsMARCO (test) | ROUGE Score40.7 | 18 | |
| Question Answering | MSMARCO (test) | F1 Score53.3 | 17 | |
| Sparse Retrieval Efficiency | MSMARCO v1 (test) | Latency @ 90% Acc (µs)156 | 16 | |
| Question Answering | MSMARCO | ROUGE-L53.9 | 15 | |
| Continual Retrieval | MSMARCO streaming topic-clustered Average | Success@576.37 | 14 | |
| Continual Retrieval | MSMARCO streaming topic-clustered (Session 9) | Success@592.2 | 14 | |
| Continual Retrieval | MSMARCO streaming topic-clustered (Session 8) | Success@592.6 | 14 | |
| Continual Retrieval | MSMARCO streaming topic-clustered (Session 7) | Success@591.9 | 14 | |
| Continual Retrieval | MSMARCO streaming topic-clustered (Session 6) | Success@589.3 | 14 | |
| Continual Retrieval | MSMARCO streaming topic-clustered (Session 5) | Success@590 | 14 | |
| Continual Retrieval | MSMARCO streaming topic-clustered (Session 4) | Success@565.9 | 14 | |
| Continual Retrieval | MSMARCO streaming topic-clustered (Session 3) | Success@568.9 | 14 | |
| Continual Retrieval | MSMARCO streaming topic-clustered (Session 2) | Success@566.7 | 14 | |
| Continual Retrieval | MSMARCO streaming topic-clustered (Session 1) | Success@569.3 | 14 | |
| Continual Retrieval | MSMARCO streaming topic-clustered (Session 0) | Success@560.6 | 14 | |
| Continual Retrieval | MSMARCO | S@596.32 | 14 | |
| Question Answering | MSMARCO Wiki-answerable | ROUGE-L57.2 | 14 | |
| Generative Question Answering | MsMARCO (dev) | ROUGE Score57.2 | 11 | |
| Question Answering | MSMARCO | F1 Score38.4 | 10 | |
| QA retrieval | MSMARCO | P@117.6 | 8 | |
| Information Retrieval | MSMARCO | QPS799 | 7 | |
| Text Retrieval | MSMARCO 100K | Hits@171.93 | 6 | |
| Text Search | MSMARCO | MRR@1044.3 | 6 |