reasoning benchmark
MuSR
MuSR (Multistep Soft Reasoning) is a benchmark for evaluating language models on multistep soft reasoning tasks specified in natural language narratives. Created through a neurosymbolic synthetic-to-natural generation algorithm, it generates complex reasoning scenarios like murder mysteries roughly 1000 words in length that challenge current LLMs including GPT-4. The benchmark tests chain-of-thought reasoning capabilities across domains involving commonsense reasoning about physical and social situations.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
MuSR leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MA | 76.4% | 100.0% | 2 | C | |
| 2 | NR | 50.7% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
MuSR highlights
The top published results on this benchmark's own scale.
What is MuSR?
Definition and scoring fields from the benchmark registry.
MuSR (Multistep Soft Reasoning) is a benchmark for evaluating language models on multistep soft reasoning tasks specified in natural language narratives. Created through a neurosymbolic synthetic-to-natural generation algorithm, it generates complex reasoning scenarios like murder mysteries roughly 1000 words in length that challenge current LLMs including GPT-4. The benchmark tests chain-of-thought reasoning capabilities across domains involving commonsense reasoning about physical and social situations.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MuSR
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- musr|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MuSR.
Which model scores highest on MuSR?
Kimi K2 Instruct is currently ranked first with 76.4%.
What does MuSR measure?
MuSR (Multistep Soft Reasoning) is a benchmark for evaluating language models on multistep soft reasoning tasks specified in natural language narratives. Created through a neurosymbolic synthetic-to-natural generation algorithm, it generates complex reasoning scenarios like murder mysteries roughly 1000 words in length that challenge current LLMs including GPT-4. The benchmark tests chain-of-thought reasoning capabilities across domains involving commonsense reasoning about physical and social situations.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.