I would love to know what the increased token count is across these models for the benchmarks. I find the models continue to get better but as they do their token usage also does. Aka is model doing better or reasoning for longer?
It's pretty wild that Brave's terms of service state as much, considering their search API is entirely derived from storing the results of other search systems. https://support.brave.app/hc/en-us/articles/4409406835469-Wh.... Aka Brave is blocking exactly what it does to Bing and Google.
I think you would be very surprised by the number of customers who don't care if the embeddings are SOTA. For every Joe who wants to talk GraphRAG + MTEB + CMTEB and adaptive rag there are 50 who just want whatever IT/prodsec has approved