Gallery, prompt v1

Exploded V60 dripper

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

The prompt, v1, frozen

Draw an exploded assembly diagram of a V60 pour-over dripper on its glass server, as an SVG. Use the cone dripper with a paper filter rather than a metal mesh filter.

Every model, its first three runs.

One square a check, in this order:

  1. All three parts
  2. Stack order
  3. Parts fit
  4. One assembly axis
  5. Labels match

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

Claude Haiku 5.5
GPT-6.1 Sol
Pareto 26.10 Preview
GPT-6 Luna

What a run cost, against checks passed.

One dot a model, over its three runs above. Further right costs more. The gap from $0.01 to $0.1 is as wide as the gap from $0.1 to $1, so the cheap models are not squeezed into a corner.

0%25%50%75%100%$0.003$0.01$0.03$0.1$0.3cost per runGPT-6.1 Sol: $0.071 a run, 15 of 15 checks passedGPT-6.1 SolGPT-6 Luna: $0.0036 a run, 14 of 15 checks passedGPT-6 LunaPareto 26.10 Preview: $0.19 a run, 13 of 15 checks passedPareto 26.10 PreviewClaude Haiku 5.5: $0.0057 a run, 12 of 15 checks passedClaude Haiku 5.5
Every dot answered this prompt with these checks, so they compare. A run that produced nothing still cost what it cost, and passed none of the checks.

How it is checked

Top to bottom: paper filter, dripper, server. The dripper is a 60 degree cone with spiral ribs and one large hole, and it sits directly on the server. Checked against Hario's V60 and Range Server pages. The server's lid is optional, so it is not required and not marked down.

All three partsby eyePaper filter, dripper and server all drawn and labelled.Pass if every listed part is drawn as a separate shape and each has a label naming it. A part only named in a label or a comment, with nothing drawn, fails it. The label must say what the part is, in any words: a name that only says where it sits ("top plate") or what it is made of, or a mention in another part's caption, does not count.
Stack ordermeasuredFilter, dripper, server, top to bottom along the axis, read from each part's coordinates in the SVG.Fail if any two drawn parts come in the wrong order along the assembly axis, read from their coordinates in the SVG and never from comments or label text.
Parts fitby eyeThe filter has the dripper's 60 degree cone angle, within 5 degrees, and the dripper's base is wider than the server's mouth, so it sits on it.Pass if each listed pair of mating parts looks as if it would go together as stated: the right angle, nested inside, or sitting on top. One pair that plainly could not fails it.
One assembly axisby eyeEvery part centred on one vertical axis, with leader lines to one side.Pass if one line runs through the middle of every part on each listed axis, and every leader line leaves from the same side. One part pushed off its axis fails it.
Labels matchby eyeEach label names the part it points at.Pass if following each leader line from its label ends on the part that label names. One label pointing at the wrong part, or at nothing, fails it.

A check decided by eye carries the rule I apply to it. I wrote those rules down on 21 September 2026, after the first results were scored, so for those results they record how I made the calls after the fact.

When this saturates: Draw it in section with coffee in it, so the bed, the filter and the ribs have to line up.

Failures seen here: false (fails when the model gets a fact wrong, such as a part in the wrong place or at the wrong size). The same kinds across every task.

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