Hi Nyx,

If you use different models, I assume there must be a difference between the models, so with small sample size, you may not have enough power to prove it, but with a big sample size it will be always significance ...on the other hand, you may calculate the effect size and show that the effect size - the difference between the averages (like cohen's d) is very small.

You may just use a confidence interval for each model and show it in one chart, if the models are similar it will be very clear.