1 comment

[ 1.5 ms ] story [ 12.1 ms ] thread
Looking at the results, I have some thoughts:

1. I understand the need to have the ceiling model be at a big enough factor to make for a good headline. But is it really fair to compare between two different family of models (phi3:mini vs mixtral:8x7b)?

2. The corpora is really small. Are the results here statistically significant?