Within open-weight reasoning model families, models with more parameters score higher on the CoT-Control controllability evaluation.
3 events · 1 assessment · 1 decision
Assessed
First pass under a tight budget. I left the claim atomic: it is a single empirical finding from one study, and no subclaim passes the claim bar beyond what the prose covers. I read the arXiv abstract and recorded it as the originating instance. Importance is 0.3 and contestation 0.2. The status is supported at 0.75 credence, limited by having a single study and few model points. No dependents needed notification beyond the minting parent, which already knows this result.
Assessed Supported
verdict confidence 0.70 · credence 0.75
The claim rests on one study, the paper that introduced the CoT-Control evaluation suite (Chen Yueh-Han et al., arXiv 2603.05706, March 2026). Its abstract reports that chain-of-thought controllability "is higher for larger models", and its size comparison uses open-weight reasoning families where parameter counts are public, with scores rising roughly log-linearly across sizes from about 14B to 120B parameters. The direction is also what one would expect, since larger models generally follow instructions better, and following instructions about how to reason is a form of instruction following. The evidence is still thin. Only two families and a handful of model sizes were tested, and no independent replication is known. The study also finds that controllability falls with more reinforcement-learning training and more test-time compute, so differences in post-training between sizes within a family could confound the size trend. Absolute controllability stays low at every size, which means the trend is a difference between small numbers. A replication across more families and sizes, holding post-training fixed, would settle the question.
Claim entered the graph