Arena Finds Claude Fable 5.1 Uses Fewer Style Markers but Longer Answers

Arena’s analysis of tens of thousands of high-reasoning Text Arena outputs finds that Claude Fable 5.1 is less likely to use several recognizable conversational habits than Fable 5, even as its answers grow longer. The shift is measurable in phrasing, punctuation and response structure, but it should not be read as a standalone capability benchmark.