Claude Fable 5.1's language is less "load-bearing" than its predecessor's

Skip to content

Sep 10, 2026

Arena.ai analyzed how Anthropic's Claude's writing changed from Fable 5 to Fable 5.1 across tens of thousands of high-reasoning Text Arena outputs. Fable 5.1 uses fewer agreement openers, fewer em dashes, and less wording like "honestly" and "frankly," while its answers have grown longer.

Stylistic features compared across Claude models. Fable 5.1 uses far fewer em dashes (11.0 per 1,000 words) than Fable 5 (16.2) but relies more on semicolons (6.09 vs. 3.73). Honesty phrases and agreeable openers also drop sharply. | Image: Arena.ai

Language complexity across Claude models showing answer length, sentence length, clause frequency, and long content word usage. Fable 5.1 writes a median of 414 words per answer, 30 percent more than Fable 5 (319) but shorter than Opus 5 (525). Sentence length sits at 12.54 words, slightly above Opus 5 at 12.20. The share of long words drops to 38.6 percent. | Image: Arena.ai