Gallery, prompt v1

A family tree of twelve coffee cultivars

One frozen prompt and every model that has run it, newest first.

Saturated since 2026-10-14

It is off the board. All 15 runs, three from each of five models, passed every check. The checks only read the brackets, so the difference between the models was in which cultivars they put together, which the post looks at.

The prompt, v1, frozen

Write an ultrametric Newick tree of twelve coffee cultivars with exactly one polytomy, of four.

Every model, its first three runs.

One square a check, in this order:

  1. Valid Newick
  2. Twelve cultivars
  3. Every tip level
  4. One split of four

passed, failed, undecided. A round mark is a check I judged by eye, and a diamond one a check a model judged.

Gemini 4 Argon
Opus 5.5
Claude Haiku 5.5
DeepSeek 4.1 Flash
GPT-6 Luna

How it is checked

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.

Valid NewickmeasuredIt reads as Newick and ends in a semicolon, no unquoted name has a blank in it, every branch has a length and none is negative, and no node has only one child.
Twelve cultivarsmeasuredTwelve tips, each with a name, no two the same, and not numbered stand-ins like T1 to T12.
Every tip levelmeasuredEvery path from the root to a tip adds up to the same length.
One split of fourmeasuredExactly one node has four children, and every other node has two.

What replaces it: Ask for the tree to follow how the cultivars were really bred, so Caturra, Pacas and Villa Sarchi have to sit with Bourbon.

The rules behind all of thisThis task's prompt, checks and any checker, on GitHub