For my personal experience, antropic model have better user experience except for 4.7 and 4.8 though. 4.7 and 4.8 feels like expensive downgrade of 4.6 to me (I didn't know why these two should even exist)

However it's less willing to obey your instruction so it's less usable for general runtine flows.

For me Anthropic models from 4.7 to 5 including where bad and ate tokens like crazy. Task delivery was worse than GPT 5.6 and token usage was 2-3x higher.

Looks like 5.5 is the new 4.6