ImageBench

vs

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 ImageBench V1 run.

replicate/google/imagen-4-ultra

API

Imagen 4 Ultra is the highest-quality tier of Google DeepMind's Imagen 4 family, targeting maximum detail and the strongest prompt alignment for brand-critical or production work. It supports up to 2K resolution with the family's typography improvements.

Maker
Google DeepMind
Family
Imagen 4
Model Size
not disclosed
unknown
Cost
$0.06 / image
high
Run Target
replicate/google/imagen-4-ultra
Effective Request
aspect_ratio: 1:1

fal/reve/2.1

API

Reve 2.1 is Reve AI's flagship text-to-image model, generating natively at 4K (4096x4096) with layout intelligence — it reasons about structure and spatial hierarchy before generating. It is a standout at in-image typography (including foreign scripts) and ranks #2 on the Text-to-Image Arena, well suited to posters, packaging, and marketing design. The older fal-ai/reve/text-to-image endpoint serves the earlier Reve Image 1.0.

Maker
Reve AI
Family
Reve Image 2.1
Model Size
not disclosed
unknown
Cost
$0.04 / image
high
Run Target
fal/reve/2.1/text-to-image
Effective Request
aspect_ratio: 1:1 · seed: 7
62.0vs74.8
Overall
62%vs80%
Capability
61.9vs69.9
Est. Preference
14.6svs45.0s
Avg Latency
Text Rendering73%100%Spatial Reasoning70%86%Human realism33%67%Truthfulness37%56%Professional Studio89%93%Graphical design83%88%Preference62%70%Latency21%0%

All 192 generations

Text Rendering73%vs100%

replicate/google/imagen-4-ultrafal/reve/2.1

Typography Style100%vs100%

Writing accuracy67%vs100%

Spatial Reasoning70%vs88%

replicate/google/imagen-4-ultrafal/reve/2.1

Attributes Binding78%vs100%

Compositionality100%vs100%

Counting56%vs100%

Negation67%vs89%

Relative Position75%vs83%

Scale & Proportions44%vs50%

Human realism33%vs64%

replicate/google/imagen-4-ultrafal/reve/2.1

Faces & Expressions33%vs89%

Full Body17%vs25%

Hands58%vs92%

Multi-Subject17%vs50%

Truthfulness37%vs56%

replicate/google/imagen-4-ultrafal/reve/2.1

Photorealism0%vs33%

Physics & Reflections33%vs50%

World Knowledge50%vs67%

Professional Studio89%vs93%

replicate/google/imagen-4-ultrafal/reve/2.1

Camera & Lighting92%vs92%

Color Precision83%vs92%

Photorealism100%vs100%

Graphical design83%vs88%

replicate/google/imagen-4-ultrafal/reve/2.1

Data Visualisation0%vs33%

Layout & Design89%vs100%

Style Diversity100%vs92%

Google Imagen 4 Ultra vs Reve 2.1: frequently asked questions