Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Reasoning benchmark
Testing the Limits of Chain-of-thought with Multistep Soft Reasoning. Every model the catalog carries a published MuSR value for, ranked by that value.
A dataset for evaluating language models on multistep soft reasoning tasks specified in natural language narratives. Tests the ability to perform complex, structured reasoning. 6 models in the ModelChoice catalog have a published value.
Each point is a model with a published MuSR value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
6 models with a published MuSR value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Narrative-based reasoning |
|---|---|---|---|
| 1 | PMTernary Bonsai 8B | Prism ML | 56.2 |
| 2 | PMTernary Bonsai 1.7B | Prism ML | 50.8 |
| 3 | PM1-bit Bonsai 8B | Prism ML | 50 |
What the benchmark measures and how its value is published, from the source’s own record.
MuSR (Testing the Limits of Chain-of-thought with Multistep Soft Reasoning) is a reasoning benchmark published by MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning. A dataset for evaluating language models on multistep soft reasoning tasks specified in natural language narratives. Tests the ability to perform complex, structured reasoning. Its evaluation set is described by the source as multi-step reasoning. The source rates its difficulty as complex reasoning tasks.
Each model's result is published by MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning as narrative-based reasoning. ModelChoice prints that value exactly as published, and never converts or rescales it. This page ranks the 6 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 |
| PM1-bit Bonsai 1.7B |
| Prism ML |
| 45.1 |
| 4 | PMTernary Bonsai 4B | Prism ML | 45.1 |
| 6 | PM1-bit Bonsai 4B | Prism ML | 41.4 |
Evidence key: Observed
Rows are ordered by the value MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.