[P] Claude vs GPT Agent Comparison

Anthropics recent announcement of tools (function calls) for Claude caught my attention, specifically this claim:

>All models can handle correcting choosing a tool from 250+ tools provided the user query contains all necessary parameters for the intended tool with >90% accuracy. These limits apply to the total number of tools, regardless of complexity. A "complex" tool would be one with a large number of parameters or parameters with complex schemas (e.g. nested objects).

This is pretty exciting news for everybody …

accuracy agent announcement anthropics apply attention claim claude comparison complexity function gpt machinelearning parameters query tool tools total