I had the opposite experience.
I had subscription to both anthropic and openai. I was out of credits for openai, so used anthropic to fix some coding issues. Spent whole weekend prompting while it kept failing over and over. Finally on Monday I had openai's weekly quota start, 2 hours issue was done.
The same thing happened again, after a couple weeks. Two weekends wasted trying to make Anthropic models to behave.
I'd think its maybe a question of getting used to a given model, developing good intuitions on how to prompt, divide work and so on? I have spent probably 2000 waking hours this year with Anthropic models, and maybe 200 on openai, so i naturally consider them easy to work with. My own benchmark suite probably reflects the way I work, which is why its mostly Anthropic models getting the top scores etc.