Artificial Analysis just published their aggregate score (61).
Still below Fable 5, let alone Fable 5.1.
EDIT: This is suspiciously low. Calls the relevance of existing benchmarks into question.
Still below Fable 5, let alone Fable 5.1.
EDIT: This is suspiciously low. Calls the relevance of existing benchmarks into question.
If it actually tackled all of the problems it was assigned, it would presumably kick Opus into the weeds.