Failure types

part-order

components stacked or connected in the wrong sequence

Seen in 14 results, across 6 models and 1 task, from 2026-09-18 to 2026-10-01. More than one model, but only one task, so it may still be the task that is hard, and the models may be fine.

Exploded French press, by Opus 5.5
Opus 5.5Exploded French press · 2026-10-01 · 4 of 5 checks
Exploded French press, by Pareto
ParetoExploded French press · 2026-10-01 · 3 of 5 checksAlso completeness
Exploded French press, by Perceptron Mk1.5
Perceptron Mk1.5Exploded French press · 2026-09-27 · 0 of 5 checksAlso completeness, physical-plausibilityTerrible
Exploded French press, by Opus 5.5
Opus 5.5Exploded French press · 2026-09-23 · 4 of 5 checksThe cleanest press on the bench, with the cross-plate on top of the mesh.
Exploded French press, by Opus 5.5
Opus 5.5Exploded French press · 2026-09-23 · 3 of 5 checksAlso physical-plausibilityRight in round 1, then it swapped the plates, and its filter is wider than the glass.
Exploded French press, by Pareto
ParetoExploded French press · 2026-09-22 · 3 of 5 checksAlso physical-plausibilityCross-plate on top of the mesh again, and plates that are the wrong diameter for the glass. Cut off by provider timeouts after round 2.
Exploded French press, by Sol
SolExploded French press · 2026-09-22 · 4 of 5 checksThe filter stack is in the right order but drawn under the carafe, which is not how it goes together.
Exploded French press, by GLM 5.3 FlashX
GLM 5.3 FlashXExploded French press · 2026-09-22 · 3 of 5 checksAlso physical-plausibilityCalls its top piece a spiral cross plate and puts the mesh at the bottom, with the lid below the whole filter and every plate wider than the carafe.
Exploded French press, by GLM 5.3 FlashX
GLM 5.3 FlashXExploded French press · 2026-09-22 · 2 of 5 checksAlso completeness, physical-plausibilityA plate missing, the cross-plate above the mesh, the lid below the filter, and plates wider than the carafe.
Exploded French press, by Qwen3.8 27B
Qwen3.8 27BExploded French press · 2026-09-22 · 3 of 5 checksAlso completenessNo spiral plate and no separate knob, and the cross retainer sits above the mesh.
Exploded French press, by Qwen3.8 27B
Qwen3.8 27BExploded French press · 2026-09-22 · 2 of 5 checksAlso completeness, physical-plausibilityA coil spring and a mesh, no cross-plate, the lid under the filter, and a mesh wider than the carafe.
Exploded French press, by GLM 5.3 FlashX
GLM 5.3 FlashXExploded French press · 2026-09-20 · 3 of 5 checksAlso completenessLeft the cross-plate out altogether, and still put the spiral plate under the mesh.
Exploded French press, by Pareto
ParetoExploded French press · 2026-09-18 · 4 of 5 checksSeven parts, one clean axis, filter stack upside down.
Exploded French press, by Sol
SolExploded French press · 2026-09-18 · 4 of 5 checksThe same inversion, glossier drawing, one round fewer.

The other types: labelling · physical-plausibility · completeness · topology · geographic-grounding

All of them, with counts · How a check is decided