It has always been like this. We actually know that the model performance has been mostly steady[0], but you cannot beat the notion of "evil companies secretly serving us worse models." The meme value is too strong.

[0]: https://marginlab.ai/trackers/claude-code/

Hmm, today's pass rate raised to 73% - interesting, are they AB-testing some new model? This is too high for Opus 4.7.