press.svg · 91 lines
<svg xmlns="http://www.w3.org/2000/svg" width="700" height="900" viewBox="0 0 700 900" font-family="Helvetica, Arial, sans-serif">
<rect width="700" height="900" fill="white"/>
<!-- center axis -->
<line x1="350" y1="30" x2="350" y2="870" stroke="#bbb" stroke-dasharray="4 6" stroke-width="1"/>
<!-- ===== LID with knob ===== -->
<g>
<!-- knob -->
<circle cx="350" cy="70" r="22" fill="#444"/>
<rect x="344" y="88" width="12" height="14" fill="#444"/>
<!-- lid dome -->
<path d="M255 150 Q255 102 350 102 Q445 102 445 150 Z" fill="#666" stroke="#333" stroke-width="2"/>
<rect x="250" y="150" width="200" height="18" rx="4" fill="#555" stroke="#333" stroke-width="2"/>
<text x="470" y="150" font-size="16" fill="#222">Lid</text>
</g>
<!-- ===== PLUNGER ROD ===== -->
<g>
<rect x="342" y="200" width="16" height="230" fill="#999" stroke="#555" stroke-width="1.5"/>
<text x="375" y="300" font-size="16" fill="#222">Plunger rod</text>
</g>
<!-- ===== FILTER ASSEMBLY (three-piece) ===== -->
<g>
<!-- cross plate (top) -->
<rect x="280" y="455" width="140" height="10" rx="3" fill="#777" stroke="#444" stroke-width="1.5"/>
<text x="470" y="462" font-size="16" fill="#222">Cross plate</text>
<!-- mesh screen (middle) -->
<rect x="280" y="500" width="140" height="8" fill="#c9c9c9" stroke="#666" stroke-width="1.5"/>
<g stroke="#888" stroke-width="0.7">
<line x1="285" y1="500" x2="285" y2="508"/>
<line x1="295" y1="500" x2="295" y2="508"/>
<line x1="305" y1="500" x2="305" y2="508"/>
<line x1="315" y1="500" x2="315" y2="508"/>
<line x1="325" y1="500" x2="325" y2="508"/>
<line x1="335" y1="500" x2="335" y2="508"/>
<line x1="345" y1="500" x2="345" y2="508"/>
<line x1="355" y1="500" x2="355" y2="508"/>
<line x1="365" y1="500" x2="365" y2="508"/>
<line x1="375" y1="500" x2="375" y2="508"/>
<line x1="385" y1="500" x2="385" y2="508"/>
<line x1="395" y1="500" x2="395" y2="508"/>
<line x1="405" y1="500" x2="405" y2="508"/>
<line x1="415" y1="500" x2="415" y2="508"/>
</g>
<text x="470" y="507" font-size="16" fill="#222">Mesh screen</text>
<!-- spiral spring -->
<path d="M280 545 q10 -18 20 0 q10 18 20 0 q10 -18 20 0 q10 18 20 0 q10 -18 20 0 q10 18 20 0 q10 -18 20 0 q10 18 20 0"
fill="none" stroke="#555" stroke-width="2.5"/>
<text x="470" y="550" font-size="16" fill="#222">Spiral spring</text>
<!-- retaining/base plate (bottom) -->
<rect x="280" y="585" width="140" height="12" rx="3" fill="#777" stroke="#444" stroke-width="1.5"/>
<text x="470" y="596" font-size="16" fill="#222">Retaining plate</text>
<!-- nut at rod end -->
<rect x="340" y="597" width="20" height="12" rx="2" fill="#555" stroke="#333" stroke-width="1.5"/>
<rect x="345" y="431" width="10" height="24" fill="#999" stroke="#555" stroke-width="1"/>
<rect x="345" y="465" width="10" height="35" fill="#999" stroke="#555" stroke-width="1"/>
<rect x="345" y="508" width="10" height="37" fill="#999" stroke="#555" stroke-width="1"/>
<rect x="345" y="545" width="10" height="40" fill="#999" stroke="#555" stroke-width="1"/>
</g>
<!-- ===== BEAKER / CARAFE ===== -->
<g>
<path d="M262 660 L262 850 Q262 862 274 862 L426 862 Q438 862 438 850 L438 660"
fill="#e8f2f5" fill-opacity="0.55" stroke="#336" stroke-width="3"/>
<!-- pour spout hint -->
<path d="M262 660 L250 645" stroke="#336" stroke-width="3" fill="none"/>
<path d="M438 660 L450 645" stroke="#336" stroke-width="3" fill="none"/>
<line x1="262" y1="660" x2="438" y2="660" stroke="#336" stroke-width="2" stroke-dasharray="2 4"/>
<path d="M438 685 C492 690 492 780 438 790" fill="none" stroke="#336" stroke-width="7"/>
<text x="470" y="830" font-size="16" fill="#222">Beaker</text>
</g>
<!-- leader lines -->
<g stroke="#888" stroke-width="0.8">
<line x1="450" y1="145" x2="466" y2="147"/>
<line x1="358" y1="295" x2="371" y2="298"/>
<line x1="420" y1="460" x2="466" y2="460"/>
<line x1="420" y1="504" x2="466" y2="504"/>
<line x1="440" y1="547" x2="466" y2="548"/>
<line x1="420" y1="591" x2="466" y2="593"/>
<line x1="438" y1="825" x2="466" y2="828"/>
</g>
<text x="350" y="895" font-size="15" fill="#555" text-anchor="middle">Exploded assembly — French press (three-piece plunger filter)</text>
</svg>round 1 of 2
Exploded French press: Kimi K3
modelmoonshotai/kimi-k3tasksvg-french-press@v2, checks c1, harness h1date2026-10-04rounds2 of 8 allowed, 12 minutes on the clockcost$0.0868thinkingmediumtokens39,011 in, 3,398 out, of which 280 reasoningtime31 sfailedAll seven parts: incomplete, component missing, major, its note said this very thing was right · Filter fits the glass: false, geometry distorted, major, cross-plate 76% of carafe, allowed 80% to 105%, its note said nothing was wrong
All seven partsdecided by looking · Pass if all seven are drawn as separate shapes and each has a label naming it. A part that is only named in a label or a comment, with nothing drawn, fails it.fail
Stack orderdecided by a number, from the filen/d
Filter fits the glassdecided by a number, from the filefail
One assembly axisdecided by looking · Pass if one vertical line runs through the middle of every part, and every leader line leaves from the same side. One part pushed off to the side fails it.pass
Labels matchdecided by looking · 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.pass
There is no post about this one, since only some results need one, so the picture, the source and the scoring are here instead.
same prompt, other modelsall 65 runs on Exploded French press →
Draw an exploded assembly diagram of a French press, as an SVG. Use the standard three-piece plunger filter rather than a two-piece travel press.Frozen at v2. This model got this and nothing else.
The standard three-piece plunger, from the top down: spiral (spring) plate, mesh screen, cross-plate. The cross-plate is the bottom piece, because its threaded stem is what the rod screws into. The spiral plate above the mesh is what presses the mesh edge out against the glass. Checked against the WebstaurantStore anatomy diagram, which is drawn exploded and labelled, and against each part's y coordinate in the SVG rather than its comment. Two-piece travel presses exist and stack differently, which is why v2 of the prompt names the design. How it is scored, and this run's files on GitHub.