IA3 vs LoRA for summarization

I am considering a PEFT method for summarization. While LoRA is wildly popular, IA3 seems more efficient. I was wondering if there is a benchmark that objectively compares IA3 to LoRA. The results in IA3 paper are rather limited in that they provide results only on a few tasks with smaller models. Please point me to any resource that would be helpful in understanding this better. Thank you