local/boogu-image-turbo Benchmark — 62/100 Overall, 192 Prompts, Every Image Shown

ImageBench V1 —

192 evaluations across 6 categories

Benchmark V1 verdicts are produced by VLM judges and can contain mistakes. Treat PASS/FAIL labels as machine-assisted assessments, and inspect the images yourself. Learn more about the methodology.

Generation Details

Source-backed model context, size, cost, and request settings for this run.

MakerBoogu

FamilyBoogu Image

Model size8B8B params

Costself-hostedfree

Latency9.9s median

Run targetlocal/boogu-image-turbo

Effective requestmodel: boogu-image-turbo · size: 1024x1024 · seed: 42

SourcesModel cardWeights & checkpoint

All 192 generations

Every challenge, grouped by category and subcategory. Solid-bordered tiles with a check passed the VLM judge; dashed tiles with a cross failed. Images are placeholders until generated.

Text Rendering

56%

Typography Style67%

Writing accuracy50%

Spatial Reasoning

72%

Attributes Binding67%

Compositionality56%

Counting44%

Negation78%

Relative Position58%

Scale & Proportions89%

Human realism

44%

Faces & Expressions25%

Full Body42%

Hands33%

Multi-Subject33%

Professional Studio

58%

Camera & Lighting25%

Color Precision50%

Photorealism67%

Graphical design

61%

Data Visualisation67%

Layout & Design56%

Style Diversity67%

Truthfulness

52%

Photorealism33%

Physics & Reflections58%

World Knowledge33%