fal/google/nano-banana-pro Benchmark — 66/100 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.

MakerGoogle

FamilyNano Banana

Model sizenot disclosedundisclosed

Cost$0.15 / imagehigh

Latency23.4s median

Run targetfal/google/nano-banana-pro

Effective requestmodel: nano-banana-pro · size: 1024x1024 · seed: 42

SourcesGoogle model docsGoogle 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

82%

Typography Style67%

Writing accuracy83%

Spatial Reasoning

83%

Attributes Binding78%

Compositionality78%

Counting89%

Negation78%

Relative Position83%

Scale & Proportions67%

Human realism

57%

Faces & Expressions50%

Full Body42%

Hands42%

Multi-Subject50%

Professional Studio

77%

Camera & Lighting75%

Color Precision75%

Photorealism67%

Graphical design

63%

Data Visualisation33%

Layout & Design44%

Style Diversity50%

Truthfulness

78%

Photorealism67%

Physics & Reflections67%

World Knowledge75%