Datasets › MS MARCO
MS MARCO (Microsoft Machine Reading Comprehension Dataset)
The MS MARCO (Microsoft MAchine Reading Comprehension) is a collection of datasets focused on deep learning in search. The first dataset was a question answering dataset featuring 100,000 real Bing questions and a human generated answer. Over time the collection was extended with a 1,000,000 question dataset, a natural language generation dataset, a passage ranking dataset, keyphrase extraction dataset, crawling dataset, and a conversational search.
Source: https://microsoft.github.io/msmarco/ Image Source: https://arxiv.org/pdf/1809.08267.pdf
Benchmarks archive 2025-07-28
All 7 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
Syntology 8 newer papers were judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Passage Ranking · MS MARCO (6 judged, 0 placed), Question Answering · MS MARCO (1 judged, 0 placed), Information Retrieval · MS MARCO (3 judged, 0 placed), Information Retrieval · MSMARCO (6 judged, 0 placed), Text Retrieval · MS MARCO (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Passage Ranking | MS MARCO | Fine-tuned SOTA MRR@10 44.3 | Text and Code Embeddings by Contrastive Pre-Training | openmatch/coco-dr | 4 | Compare |
| Passage Re-Ranking | MS MARCO | HLATR MRR 0.42 | HLATR: Enhance Multi-stage Text Retrieval with Hybrid... | Alibaba-NLP/HLATR | 4 | Compare |
| Question Answering | MS MARCO | Masque Q&A Style Rouge-L 52.2 | Multi-style Generative Reading Comprehension | — | 4 | Compare |
| Information Retrieval | MS MARCO | ConAE-128 Time (ms) 0.3245 | Dimension Reduction for Efficient Dense Retrieval via... | neuir/conae | 3 | Compare |
| Information Retrieval | MSMARCO | RetroMAE MRR@10 0.416 | RetroMAE: Pre-Training Retrieval-oriented Language... | staoxiao/retromae | 1 | Compare |
| Passage Retrieval | MS MARCO | TW-BERT MAP 0.2025 | End-to-End Query Term Weighting | ledmaster/tw-bert | 1 | Compare |
| Text Retrieval | MS MARCO | Lucene (BM25S) NDCG@10 22.8 | BM25S: Orders of magnitude faster lexical search via... | xhluca/bm25s +2 | 1 | Compare |
Papers archive 2025-07-28
papers with a benchmark row: 14 · with a code link: 11 · where Syntology ran a sample: 5 (4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all papers with a benchmark rowonly where code ran (5 of 14 with a benchmark row: 4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 14 of 14 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).
The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 1,036. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.
Dataset loaders archive 2025-07-28
3 loaders as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
Custom (research-only, non-commercial)
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- MS MARCO
- MSMARCO
2 variant names, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections