Claude Opus 5.5 uses 95% fewer em dashes, but its answers are getting longer
At a glance
- Severity
- Low
- Used in attacks
- No flaws named
- Reported by
- 1 outlet
Anthropic's Claude Opus 5.5 appears to be changing how it writes, with new analysis showing fewer obvious AI writing patterns, shorter sentences, and simpler wording compared with Opus 5.
Claude Opus 5.5 is not only one of the best models for coding, but it also appears to be a bit better at writing, as Anthropic appears to be changing how AI writes.
According to Arena, an AI benchmarking tool, Opus 5.5 has fewer obvious AI writing patterns, so you're less likely to create AI slop content with this model.
It also found that sentences are now shorter, which means you have fewer long sentences and simpler wording compared with Opus 5.
Arena analyzed high-reasoning Text Arena responses from August and September 2026 and observed that 10 of 12 writing measures moved in what it considers a better direction.
Interestingly, Arena's data confirms that Opus has almost stopped using em dashes, which was one of the biggest signs of AI-generated content.
Opus 5 used 15.2 em dashes per 1,000 words, while Opus 5.5 dropped that figure to just 0.8, a reduction of roughly 95%. It also found that semicolon usage fell sharply from 6.10 to 1.64 per 1,000 words.
The newer model writes shorter sentences, averaging 10.03 words compared with 12.14 for Opus 5. However, there is one obvious tradeoff, and that is that Opus 5.5 is more verbose.
In other words, average answers increased from 453 to 481 words, making it the longest-writing Opus model in the comparison.
More lately, AI models have focused mostly on the coding side of things, so it's quite interesting to watch Anthropic change how Claude writes, and if anything, you'll see fewer em dashes on the internet.
Build your security blueprint for AI-powered attacks
Join Mikko Hyppönen and security leaders from the NFL, CHANEL, and Atlassian for a two-hour digital summit on what AI-speed attacks change, what defenders should stop doing, and how to validate, decide, fix, and re-validate at machine speed.
Reproduced in full under licence from BleepingComputer. © BleepingComputer. Written by Mayank Parmar.
Fastnexa security experts
Dealing with this in your own company?
If this story touches software, suppliers or systems you use, a Fastnexa security expert can tell you what it means for you and what to do first.
Think you’ve already been hit? Don’t wait on a form: call or WhatsApp +1 (732) 454 2616. We reply within 1 hour, 24/7. Emergency help →
Coverage
One outlet has carried this so far.
2026-09-26 16:26 UTC
Related stories
- OpenAI pauses some training amid allegations its rogue agents behaved more badly than first thought
The Register · 2026-09-28
- OpenAI is preparing “o,” an always-on ChatGPT assistant that could handle email
BleepingComputer · 2026-09-27
- Anthropic turns Claude into an AI marketplace with 2,000+ plugins and connectors
BleepingComputer · 2026-09-27
- China and US Agree to Establish AI Safety Channel and Continue Trade and Military Talks
SecurityWeek · 2026-09-26
- OpenAI's AI agents accidentally uploaded user-provided images to third-party sites
BleepingComputer · 2026-09-26