New AA intelligence index v5 with “Private tests” conveniently upranks GPT, Google’s models, while open weights chinese models downrank

The new Artificial Analysis intelligence index v5 is facing criticism for its introduction of "private tests" on private datasets. This change has reportedly led to a significant downranking of current open-weights models, particularly Chinese models, while conveniently upranking models from GPT and Google. The community finds this shift suspicious, questioning the transparency and methodology behind the v5 index's scoring.