benchmarks.wiki / Public workspace

MuSR

Reasoning

MuSR poses multistep soft reasoning problems over algorithmically generated narratives. It has three domains — murder mysteries, object placements and team allocation — and this catalogue imports all three domains, 756 problems in total.

musr

Full text756 tasks

Official source

Full text: eligible public problems include text, images and discussion.

History

Zayne Sprague and collaborators introduced MuSR in 2023 to study multistep reasoning in narratives where individual clues require commonsense interpretation. The benchmark covered murder mysteries, object placement, and team allocation rather than relying only on explicitly stated logical rules. The catalogue lists TAUR-Lab as the source maintainer and records the Hugging Face dataset publication in May 2024.

How it was built

MuSR uses algorithmically generated narratives across three domains: murder mysteries, object placement and team allocation. Each problem presents a narrative, a question and candidate answers, while the reference data identifies the correct option. This catalogue records 250 problems in the murder-mystery selection and imports 200 of them, rather than representing all three domains.

At a glance

What a problem looks like

A narrative of several hundred words, a question about it, and the candidate answers as a list. The correct index is not part of the prompt.

Read an actual problem

How it is scored

The source ships the answer index and the chosen option; this catalogue keeps both in restricted storage and never renders them.

Metric: accuracy over the 250 problems in each domain

Why it is hard

The clues are spread through a long narrative and none of them decides the answer alone. The chain has to be assembled from commonsense inferences that the text never states.

Limitations and criticism

The generated narratives provide a controlled setting but do not establish performance on unrestricted real-world reasoning. Multiple-choice accuracy measures selection of the reference option without directly verifying the reasoning used to reach it. The murder-mystery selection also cannot substitute for an aggregate across object placement and team allocation, whose reasoning demands differ.

Cite

@article{sprague2023musr,
  title={MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning},
  author={Zayne Sprague and Xi Ye and Kaj Bostrom and Swarat Chaudhuri and Greg Durrett},
  journal={arXiv preprint arXiv:2310.16049},
  year={2023}
}

Discussion

1 thread and 0 posts on this page. Anyone may reply; no account is required.

Contribute

Share a reproduction, report an evaluation issue, or suggest a correction to this benchmark overview.

Tasks

Whole public benchmark.

Public problems
756
Formats
text (756)
Problems with images
0
Answer availability
Answer published by the source (756)
Configs
default (756)
Splits
murder_mysteries (250) · object_placements (256) · team_allocation (250)
Awaiting a first discussion
756
Problems with a discussion
0
Public contributions
0

Provenance and terms

Pinned source revisions, newest first:

  • 7c365b439a222150f317764d4f16ae6c96d7d94a · acquired 2026-09-23 · release 4eea9fa15522
  • 7c365b439a222150f317764d4f16ae6c96d7d94a · acquired 2026-09-12 · release 2a1b3a07a10a