This is a great idea, but I think it would also be great for users to have quick access to provider's claims about their model's purpose, as well as Kagi's own benchmark results, for each model.
Additionally, @dps had a great suggestion (on the idea above), to allow for some sort of community polling for LLMs. I would surface this information here as well.
This would give users the ability to quickly make a decision on what model to choose, based on multiple data points, rather than the current trial and error process, or having Kagi decide for us.
Ideally, I would like to see a tool-tip appear when hovering over each model, and have that display Kagi benchmarks, provider claims, community polling results, and a privacy score. Based on that information, users could select the best model for their needs.
