I've been testing sol, and opus, almost weekly as new models are released. I haven't seen any evidence of the nerfing conspiracy theories. https://slopcop.com/power-ranking
Edit: But it does look like you get about 20% less tokens for your subscription with OpenAI than you did until a couple months ago.
Do you use subscriptions or API for this testing? I suspect it's only the subscriptions that are impacted.