# A 30-Day Benchmark Now Tracks Whether Claude Opus 5.5 Has Quietly Degraded

LiveNerf runs a calibrated daily panel against the model's launch-week performance after users alleged a drop, and a separate retest put it at 99.2 percent of its starting score.

- Published: 2026-09-30T06:34:52.927Z
- Canonical: https://polylog.news/ai/2026-09-30/a-30-day-benchmark-now-tracks-whether-claude-opus-5-5-has-qu
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Hacker News](https://github.com/ninjahawk/livenerf), [Anthropic News](https://www.anthropic.com/claude-opus-5-5)

Within days of Claude Opus 5.5 shipping on September 22, users began claiming the model had degraded after launch, describing weaker answers and more frequent refusals. The complaint recurs with every major model release and has never been…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-30/a-30-day-benchmark-now-tracks-whether-claude-opus-5-5-has-qu (subscription information: https://polylog.news/pricing).