0 of 5 models asked a question written entirely in Yoruba, in its own script, answered it correctly. Answering in English is a failure here, not a pass — a model with no coverage cannot parse the question in the first place. Every verdict below is signed by the machine that took it.
On the page on purpose. These are the models a “multilingual” label would have sold you, and the reason the list above is worth anything.
A model absent from both lists was never asked in Yoruba, and that is not a claim either way. The probe set covers a fixed list of languages; a script missing from it is missing from the evidence, not from the model.
← Every model this network has measured