Just to confirm, you will be benchmarking models other than OpenAI models using this dataset and you aren’t contractually prevented from doing this right?
(The original blog post cites scores of models from multiple developers, so I assume so.)
Yes.
Just to confirm, you will be benchmarking models other than OpenAI models using this dataset and you aren’t contractually prevented from doing this right?
(The original blog post cites scores of models from multiple developers, so I assume so.)
Yes.