Datasets › MS MARCO

MS MARCO (Microsoft Machine Reading Comprehension Dataset)

Introduced by Payal Bajaj et al. in MS MARCO: A Human Generated MAchine Reading COmprehension Dataset1 Jan 2016 archive 2025-07-28

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.

Papers archive 2025-07-28

14 shown of 14 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 1,036. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
BM25S: Orders of magnitude faster lexical search via eager sparse scoring 3 1 4 Jul 2024 ran 10 of 22 samples (12 unverified)
End-to-End Query Term Weighting 1 1 6 Aug 2023 not harvested
RetroMAE v2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models 1 1 16 Nov 2022 not harvested
RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder 1 1 24 May 2022 not harvested
HLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer Reranking 1 1 21 May 2022 not harvested
Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder 1 2 6 May 2022 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Text and Code Embeddings by Contrastive Pre-Training 1 4 24 Jan 2022 not harvested
Document Expansion by Query Prediction 5 1 17 Apr 2019 ran 3 of 3 samples (0 unverified)
An Updated Duet Model for Passage Re-ranking 1 1 18 Mar 2019 not harvested
Passage Re-ranking with BERT 6 1 13 Jan 2019 ran 2 of 13 samples (11 unverified)
Multi-style Generative Reading Comprehension 0 1 8 Jan 2019 not harvested
A Deep Cascade Model for Multi-Document Reading Comprehension 0 1 28 Nov 2018 not harvested
Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification 0 1 6 May 2018 not harvested
Bidirectional Attention Flow for Machine Comprehension 27 1 5 Nov 2016 ran 8 of 11 samples (3 unverified; 7 pointer-only for licence)

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