← Back to context Comment by chvid 5 months ago They leak the second they are used on a model behind an API, don't they? 1 comment chvid Reply chvid 5 months ago As far as I can tell the only way of doing a comparison of two models, that cannot be easily gamed, is being having them in open weights form and then running them against a benchmark that was created after both of the two models were created.
chvid 5 months ago As far as I can tell the only way of doing a comparison of two models, that cannot be easily gamed, is being having them in open weights form and then running them against a benchmark that was created after both of the two models were created.
As far as I can tell the only way of doing a comparison of two models, that cannot be easily gamed, is being having them in open weights form and then running them against a benchmark that was created after both of the two models were created.