I think there's a question of semantics here. RL is way more expensive in terms of compute, as you have to generate a significant amount of output before you can judge whether it's good or bad. So compute is one angle, but another is how much impact RL has on the weights vs pre-training
I cannot see how cost is relevent. What we're discussing is impact.
Apparently the impact of RLVR is generally bigger, otherwise AI companies would spend more of their compute budget on pre-training. The former seems to be more effective.
That kinda presumes more pre-training compute would significantly help. There is a diminishing returns curve.