yeah i think so, although opus would be much less lazy than gpt-5 if it was put in an ethically complicated situation! gpt-5 would probably just say "sorry, I cant help with that" or fail to notice the ethical issue...

opus 3 is a much more well-rounded and situationally aware intelligence, whereas gpt-5 is hyperoptimized to not only be very competent but try very hard on the object level to succeed at whatever it's asked, without orienting itself in why or whether the request makes sense