bfl/flux-2-pro Benchmark — 60/100 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 $0.03 / imagelow

Latency11.8s median

Run targetbfl/flux-2-pro

Effective requestmodel: flux-2-pro · 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

56%

Typography Style67%

Writing accuracy42%

Spatial Reasoning

53%

Attributes Binding56%

Compositionality56%

Counting44%

Negation44%

Relative Position42%

Scale & Proportions44%

Human realism

73%

Faces & Expressions75%

Full Body58%

Hands58%

Multi-Subject67%

Professional Studio

69%

Camera & Lighting75%

Color Precision75%

Photorealism67%

Graphical design

53%

Data Visualisation33%

Layout & Design44%

Style Diversity42%

Truthfulness

73%

Photorealism0%

Physics & Reflections67%

World Knowledge58%