bfl/flux-2-klein-4b Benchmark — 50/100 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.

MakerBlack Forest Labs

FamilyFLUX.2

Model sizenot disclosedundisclosed

Costfrom $0.014 / imagelow

Latency3.8s median

Run targetbfl/flux-2-klein-4b

Effective requestmodel: flux-2-klein-4b · size: 1024x1024 · seed: 42

SourcesBlack Forest Labs model docsBlack Forest Labs pricing

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

53%

Typography Style33%

Writing accuracy50%

Spatial Reasoning

47%

Attributes Binding33%

Compositionality44%

Counting56%

Negation33%

Relative Position25%

Scale & Proportions33%

Human realism

38%

Faces & Expressions42%

Full Body17%

Hands25%

Multi-Subject50%

Professional Studio

55%

Camera & Lighting58%

Color Precision50%

Photorealism33%

Graphical design

44%

Data Visualisation33%

Layout & Design56%

Style Diversity25%

Truthfulness

42%

Photorealism0%

Physics & Reflections33%

World Knowledge33%