Gallery, prompt v1
Exploded portafilter
One frozen prompt and every model that has run it, newest first.
The prompt, v1, frozen
Draw an exploded assembly diagram of an espresso machine portafilter, as an SVG. Use a double-spout portafilter with a removable basket rather than a bottomless one.
Every model, its first three runs.
One square a check, in this order:
- All five parts
- Stack order
- Parts fit
- Two assembly axes
- Labels match
passed, failed, undecided. A round mark is a check I judged by eye, and a diamond one a check a model judged.
| DeepSeek 4.1 Flash | |||
| GLM 5.3 FlashX | |||
| Opus 5.5 | |||
| Claude Haiku 5.5 | |||
| Mistral Large 4 | |||
| 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.
How it is checked
On a vertical axis, top to bottom: filter basket, retaining spring, portafilter body, double spout. The handle is on a horizontal axis off the body, so this is the one member with two axes. Checked against parts sellers, since no maker's exploded diagram could be fetched: Espresso Parts and Zirkus Coffee on the spring that clips into a groove inside the body and grips the basket rim, Espresso Parts on the spout that screws onto the bottom of the body, and Nepo Coffee on handles that screw onto a stud on its side.
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 locked into the group head in section, so the basket, the gasket and the shower screen have to meet.
Failures seen here: incomplete (fails when the model leaves out something the brief asked for); false (fails when the model gets a fact wrong, such as a part in the wrong place or at the wrong size); unreadable (fails when the content may be right, but a reader can't make it out). The same kinds across every task.
The rules behind all of thisThis task's prompt, checks and any checker, on GitHub




















