Arena.ai 分析：Claude Fable 5.1 的语言比前代更不"承重"

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

Median response length rises 30 percent from 319 to 414 words but remains 21 percent shorter than Opus 5's 525 words. Stock phrases such as "load-bearing" fall 20 percent per 1,000 words, hedges like "perhaps" and "arguably" fall 36 percent, and praise and validation appear in 1.98 percent of responses, down from 3.17 percent. Long content words fall from 42.6 percent to 38.6 percent, while abstract nouns drop 25 percent, from 4.39 to 3.28 per 100 words.