Failure types

labelling

labels that don't match what is drawn

Seen in 32 results, across 11 models and 2 tasks, from 2026-09-22 to 2026-09-29. More than one model and more than one task, so it is more than a quirk of either.

A three-set coffee Venn diagram, by Claude Sonnet 5.5
Claude Sonnet 5.5A three-set coffee Venn diagram · 2026-09-29 · 1 of 4 checksOverlaping labels with lines.
A three-set coffee Venn diagram, by GPT-6 Sol
GPT-6 SolA three-set coffee Venn diagram · 2026-09-27 · 3 of 4 checks
A three-set coffee Venn diagram, by Perceptron Mk1.5
Perceptron Mk1.5A three-set coffee Venn diagram · 2026-09-27 · 2 of 4 checks
A three-set coffee Venn diagram, by Perceptron Mk1.5
Perceptron Mk1.5A three-set coffee Venn diagram · 2026-09-27 · 2 of 4 checks
A three-set coffee Venn diagram, by Perceptron Mk1.5
Perceptron Mk1.5A three-set coffee Venn diagram · 2026-09-27 · 2 of 4 checks
A three-set coffee Venn diagram, by Command A+
Command A+A three-set coffee Venn diagram · 2026-09-27 · 2 of 4 checks
A three-set coffee Venn diagram, by Command A+
Command A+A three-set coffee Venn diagram · 2026-09-27 · 3 of 4 checks
A three-set coffee Venn diagram, by Command A+
Command A+A three-set coffee Venn diagram · 2026-09-27 · 2 of 4 checks
Exploded French press, by Perceptron Mk1.5
Perceptron Mk1.5Exploded French press · 2026-09-27 · 0 of 5 checksAlso completeness, physical-plausibilityNot great and off axis
Exploded French press, by Perceptron Mk1.5
Perceptron Mk1.5Exploded French press · 2026-09-27 · 0 of 5 checksAlso completeness, physical-plausibility
Exploded French press, by Command A+
Command A+Exploded French press · 2026-09-27 · 0 of 5 checksAlso completeness, physical-plausibility
Exploded French press, by Command A+
Command A+Exploded French press · 2026-09-27 · 0 of 5 checksAlso completeness, physical-plausibility
Exploded French press, by Command A+
Command A+Exploded French press · 2026-09-27 · 0 of 5 checksAlso completeness, physical-plausibilityTerrible
A three-set coffee Venn diagram, by Kimi K3
Kimi K3A three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksEvery drink in its region, with milkshake across an edge.
A three-set coffee Venn diagram, by Kimi K3
Kimi K3A three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksFour labels across an edge after one render, which it called done.
A three-set coffee Venn diagram, by Kimi K3
Kimi K3A three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksThree labels across an edge after one render.
A three-set coffee Venn diagram, by Ember 1
Ember 1A three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksCircles turned on their side, and four labels across an edge.
A three-set coffee Venn diagram, by Ember 1
Ember 1A three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksPlain outlines, every drink right, and three labels across an edge.
A three-set coffee Venn diagram, by Ember 1
Ember 1A three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksEvery drink right, with iced long black and milkshake on a line.
A three-set coffee Venn diagram, by GPT-6 Sol
GPT-6 SolA three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksEvery drink right, and iced latte across a line.
A three-set coffee Venn diagram, by GPT-6 Luna
GPT-6 LunaA three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksEvery drink right, and five labels across an edge.
A three-set coffee Venn diagram, by GPT-6 Luna
GPT-6 LunaA three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksEvery drink right, and three labels across an edge.
A three-set coffee Venn diagram, by GPT-6 Luna
GPT-6 LunaA three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksEvery drink right, and three labels across an edge.
A three-set coffee Venn diagram, by GLM 5.3 FlashX
GLM 5.3 FlashXA three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksEvery drink right, and four labels across an edge.
A three-set coffee Venn diagram, by GLM 5.3 FlashX
GLM 5.3 FlashXA three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksServed cold on top, every drink right, and four labels across an edge.
A three-set coffee Venn diagram, by Grok 4.7
Grok 4.7A three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksPour-over inside Has espresso and milkshake in milk only.
A three-set coffee Venn diagram, by Grok 4.7
Grok 4.7A three-set coffee Venn diagram · 2026-09-25 · 2 of 4 checksEight rounds, with milkshake broken over two lines as "milk shake" and iced long black on a line.
A three-set coffee Venn diagram, by Grok 4.7
Grok 4.7A three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksEvery drink right, and only iced long black touching a line.
A three-set coffee Venn diagram, by MiMo v2.6 Pro
MiMo v2.6 ProA three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksEvery drink right, and two labels across an edge. The clock ended it after one render.
A three-set coffee Venn diagram, by MiMo v2.6 Pro
MiMo v2.6 ProA three-set coffee Venn diagram · 2026-09-25 · 3 of 4 checksEvery drink right, and two labels across an edge. The clock ended it after one render.
A three-set coffee Venn diagram, by DeepSeek 4.1 Flash
DeepSeek 4.1 FlashA three-set coffee Venn diagram · 2026-09-22 · 3 of 4 checksEvery drink in the right region, and six of the eight labels lying across a circle's edge.
A three-set coffee Venn diagram, by DeepSeek 4.1 Flash
DeepSeek 4.1 FlashA three-set coffee Venn diagram · 2026-09-22 · 3 of 4 checksTwo labels across an edge, with white boxes behind them that hide the line they cross.

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

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