ChatGPT
It’s a catchy rule of thumb, not a reliable ranking. Each is general-purpose, and the best choice depends on the model version, tools, and your task.
My practical advice: try the same real task on two or three assistants and compare accuracy, effort required, speed, and cost. For research, check whether the cited sources actually support the answer. For coding, run the tests.
Bottom line: those labels describe reputations—not fixed capabilities.