"95% probability B beats A" and "p=0.05" answer different questions.

"95% probability B beats A" and "p=0.05" answer different questions.
Frequentist p-value: chance of this data if A=B. Bayesian posterior: chance B>A given the data. Stakeholders want the second; classical tests deliver the first. The mismatch breeds bad readouts.

— Bayesian methods also need a prior — yours isn't "objective," just explicit.
— Pick one framework per test and report its actual claim.

Read the number, not the story. [framework stated up front]