Newick: coffee cultivar tree, by claude-opus-5.5
claude-opus-5.5 · round 3 of 3 · seed 2$0.06SVGtree.nwk
tree.nwk · 2 lines
(((((Caturra:2,Pacas:2,'Villa Sarchi':2,Catuai:2):2,(SL28:1,SL34:1):3):2,Bourbon:6):1,((Maragogipe:2,Pacamara:2):3,(Typica:4,'Mundo Novo':4):1):2):3,Geisha:10);
round 1 of 3
A family tree of twelve coffee cultivars, by Opus 5.5, the render after round 1
123What the model saw after each round. The picture above is the round that was scored, round 3.
gallery/A family tree of twelve coffee cultivars/Opus 5.5, run 2

Caturra, Pacas, Villa Sarchi and Catuai are the split of four, with Bourbon outside them.

modelanthropic/claude-opus-5.5tasknewick-coffee-cultivars@v1, checks c1, harness h1date2026-10-14rounds3 of 8 allowed, 12 minutes on the clockcost$0.0622thinkingmediumtokens20,912 in, 2,294 out, of which 1,167 reasoningtime44 s
Valid Newickdecided by a number, from the filepass
Twelve cultivarsdecided by a number, from the filepass
Every tip leveldecided by a number, from the filepass
One split of fourdecided by a number, from the filepass
read the post
its other runs
A family tree of twelve coffee cultivars, by Opus 5.5, run 1run 1 · 1r · $0.0447Bourbon, Caturra, Pacas and Villa Sarchi make the split of four.A family tree of twelve coffee cultivars, by Opus 5.5, run 3run 3 · 2r · $0.0476Caturra and Villa Sarchi sit under Bourbon, and the split of four is the Kenyan lines.
same prompt, other modelsall 15 runs on A family tree of twelve coffee cultivars →
the prompt it was given
Write an ultrametric Newick tree of twelve coffee cultivars with exactly one polytomy, of four.
Frozen at v1. This model got this and nothing else.
ground truth

The tree read with Biopython, every path from the root to a tip added up from its branch lengths, and the children of every node counted. The checks only read the brackets. Whether a cultivar sits beside its relatives is not checked here, and the post of 14 October looks at that by eye. How it is scored, and this run's files on GitHub.