Thus, a satisfaction score from April may not mean the same thing in July, even for the same model. Side-by-side votes hold up better: every model answers the same prompt for the same user at the same moment, so they all face the same bar.
Read our interactive version at https://www.designarena.ai/blog/ai-models-more-complaints-over-time, and try making your own generations on http://DesignArena.ai.