Sept 2024 was when OpenAI announced its new model - not an LLM but a "chain of thought" model built on LLMs. This represented a turn away from the "scale is all you need to reach AGI" idea by its top proponent.
Whatever the case, there are open platforms that give users a chance to compare two anonymous LLMs and rank the models as a result [1].
What I observe when I look for these rankings is that none of the top ranked models come from before your stagnation cut off date of September 2024 [2].