One living number for a question with no leaderboard: how much of the model mind is shared? Measured behaviourally — from what the models reach for when nothing is asked of them — not by opening the box.
Give every model family the same coordinates — a shared vocabulary of association nodes — and you can ask a precise question: do families share one association geometry, or does each have its own? The index is the cross-family correlation divided by the within-family reliability ceiling. At 1.0, families resemble each other as much as they resemble themselves — one shared map. At 0, every family is its own world. It sits at 0.86: the families share most of the association structure that is even measurable.
It is a measurement, not a slogan — dated, re-derivable, and it moves as the corpus grows.
The number is alive. As more independent labs are added it has drifted 0.80· 15 families → 0.89· 39 → 0.86· 49, today — re-derived here in ~1 second from a committed cache, faithful to the makers' own code. The drift is the product: a standing reading, not a one-off claim.
The load-bearing surprise: a family's map does not get richer with model size. Below, each point is one family — how many billions of parameters (across) against how multidimensional its association geometry is (up). If bigger models built richer maps, the cloud would tilt up. It doesn't.
There is no statistically significant trend either way. The biggest models span the whole range — the richest map belongs to a frontier model, but so do two of the leanest (both 670B), while a 12B model sits near the top. The shared structure is inherited from language, not manufactured by scale: the models are the telescope, not the sky.
The index will move as the family set grows, and it is reported at the coarse (50-node) resolution, where the read is most reliable; finer node sets are noisier and lower. It says nothing about whether the shared map is correct — only that it is real and measured. It is the behavioural complement to the convergence the representation-probing literature finds inside the models: same thesis, measured from the outside, needing no weights. Every figure here recomputes from the corpus — research/the-map/derive_universality.py over a committed node-sequence cache, asserted against the makers' own the_map.universality — so the index can't quietly drift from what the data says.
See the convergence with your own eyes — take the Hive Mind Test, ask the map a word, meet the shared cast, or fly the whole map.