tree.nwk · 2 lines
((Geisha:0.60,Java:0.60):0.40,(((Typica:0.25,Blue_Mountain:0.25):0.25,(Kona:0.30,Maragogipe:0.30):0.20):0.30,((SL28:0.30,SL34:0.30):0.25,(Bourbon:0.25,Caturra:0.25,Pacas:0.25,Villa_Sarchi:0.25):0.30):0.25):0.20);Bourbon, Caturra, Pacas and Villa Sarchi make the split of four, and Blue Mountain sits with Typica.
modelgoogle/gemini-4-argontasknewick-coffee-cultivars@v1, checks c1, harness h1date2026-10-14rounds1 of 8 allowed, 12 minutes on the clockcost$0.0905thinkingmediumtokens28,858 in, 4,533 out, of which 3,780 reasoningtime1 min 19 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
run 1 · 1r · $0.0554Bourbon, Caturra, Pacas and Villa Sarchi make the split of four, and Kona and Blue Mountain sit with Typica.
run 2 · 1r · $0.0862Bourbon, Caturra, Pacas and Villa Sarchi make the split of four, and Kona sits with Typica.same prompt, other modelsall 15 runs on A family tree of twelve coffee cultivars →
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.
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.