Thanks. I'm really no expert (:P) on MoE research; I just noticed what was written in the Soft MoE paper and felt a need to check.

The non-deterministic outputs are really similar, yeah, if you check the gist examples I linked https://gist.github.com/152334H/047827ad3740627f4d37826c867a.... This part is at least no surprise, since the randomness should be bounded.

I suspect OpenAI will figure out some way to reduce the randomness at some point, though, given their public commitment to eventually adding logprobs back to ChatCompletions.