card: answer length from the final run

README.md

@@ -20,7 +20,7 @@ nothing: no solver, no example solutions, no human data.
 - Built as a control for [RubiksBench](https://brianbriscoe.dev/lab/rubiksbench),
   where language models must write the whole answer in one reply. On the same
   full scrambles the best of them, GPT-6 Astra, solves 9 of 10 with answers
-  averaging over 100 moves; this model's answers average about 21. It is not the
+  averaging over 100 moves; this model's answers average about 22. It is not the
   same test: this model gets a search loop, the language models get one reply.
 
 Write-up and replays: https://brianbriscoe.dev/lab/tiny-cube-solver
@@ -119,7 +119,7 @@ no harder than 20. A full scramble takes about 80 to 90 seconds on one RTX A6000
 
 - It is not fast. The Kociemba two-phase solver solves any cube in milliseconds.
   This model exists to show that a small network can learn the task at all.
-- Solutions are not guaranteed to be shortest. Full scrambles average about 21
+- Solutions are not guaranteed to be shortest. Full scrambles average about 22
   moves.
 - 3x3x3 only.