Here is a comparison with 308. I used his numbers and inputed them in my model. You can compare these results to 308's ones here. Both models give similar results, even though there are still differences in the Atlantic and in Ontario. For the former, my guess is it depends if we assume that the effects such as the ABC campaign are gone or not. I might revise my decision to assume that 50% of those effects are gone later. Depending of some polls during the next campaign.
At the end, with 308 and DemocraticSpace (whcih I'm sure we'll be active during the campaign), I think people have enough choices regarding riding-level projections (you also have other sites, such as cdn election watcher). I personally see the different models as all providing some truth. A little bit like it's better to have more than one poll, it's better to have more than one model. Even though, at the end, for one specific election, one model will of course be better. And so far, only my website allows everyone to use the model.