Benchmark
MuSR
MuSR (Multistep Soft Reasoning) is a benchmark for evaluating language models on multistep soft reasoning tasks specified in natural language narratives…
- Modality
- text
- Categories
- reasoning
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 2
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Hermes 3 70B | Nous Research | 0.5067 | 2024-08-15 | evidence |
| Kimi K2 Instruct | Moonshot AI | 0.764 | 2025-07-11 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.