跳到正文
Rohan Paul· @rohanpaul_ai · X·AI 评分49
AI 导读

对 Claude Opus 5.5 与 Opus 5 高推理文本输出的分析显示，12 项写作指标中 10 项改善：破折号从每千词 15.2 降至 0.8（降 95%），分号降 73%，长实词占比从 41.7% 降至 38.6%，平均句长从 12.14 词缩短至 10.03 词（降 17%）。

正文 · 原文

Claude Opus 5.5 simply writes better.

Em dashes fall from 15.2 to 0.8 per 1,000 words, a 95% drop, while semicolons fall 73%.

But Opus 5.5 did not become terse. It actually became 6% longer, from 453 to 481 words per answer, while average sentence length fell 17%, from 12.14 to 10.03 words.

引用Arena.ai@arena

We analyzed how @claudeai’s Opus 5.5 writes compared with Opus 5 across high-reasoning Text Arena outputs.

10 of 12 writing measures moved in a better direction.

Opus 5.5 should be easier to read:

  • Long content words fall from 41.7% to 38.6%, the lowest share of any Claude model we analyzed.
  • Sentences are 17% shorter on average, dropping from 12.14 to 10.03 words.

The tradeoff is length. Answers get 6% wordier, rising from 453 to 481 words on average, making Opus 5.5 give the longest answers across the Opus family.

It also sounds less recognizably AI on two familiar tells:

  • 95% fewer em dashes
  • 73% fewer semicolons

But a new giveaway may be emerging. Hedges and caveats such as “perhaps” and “arguably” rise 97%, from 0.39 to 0.77 per 1,000 words, the highest rate of any Claude model we analyzed.

What do you think: does Opus 5.5 read more naturally?

在 X 查看被引用的帖子

来源：Rohan Paul · x.com

Anthropic / Claude

事件后续 · 8+

查看事件全部