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.

openai/gpt-image-2

API

GPT Image 2 is OpenAI's current image generation and editing model for fast, high-quality image creation, with flexible image sizes and high-fidelity image inputs through the OpenAI Images API.

Maker
OpenAI
Family
GPT Image
Model Size
not disclosed
unknown
Cost
token-based
high
Run Target
openai/gpt-image-2
Effective Request
model: gpt-image-2 · size: 1024x1024 · quality: auto

fal/bytedance/seedream-v4

API

Seedream 4.0 is ByteDance Seed's unified image creation model for text-to-image and editing, aimed at multimodal generation, reference consistency, knowledge-based prompts, and high-resolution output.

Maker
ByteDance Seed
Family
Seedream
Model Size
not disclosed
unknown
Cost
$0.03 / image
high
Run Target
fal/fal-ai/bytedance/seedream/v4/text-to-image
Effective Request
image_size: square_hd · num_images: 1 · seed: 7
78.5vs59.4
Overall
84%vs63%
Capability
73.0vs56.2
Est. Preference
45.3svs14.1s
Avg Latency
Text Rendering100%87%Spatial Reasoning91%75%Human realism55%33%Truthfulness74%41%Professional Studio100%74%Graphical design100%79%Preference73%56%Latency0%22%

All 192 generations

Text Rendering100%vs87%

openai/gpt-image-2fal/bytedance/seedream-v4

Typography Style100%vs100%

Writing accuracy100%vs83%

Spatial Reasoning91%vs75%

openai/gpt-image-2fal/bytedance/seedream-v4

Attributes Binding100%vs100%

Compositionality100%vs89%

Counting89%vs56%

Negation100%vs56%

Relative Position83%vs83%

Scale & Proportions78%vs67%

Human realism55%vs33%

openai/gpt-image-2fal/bytedance/seedream-v4

Faces & Expressions92%vs83%

Full Body17%vs8%

Hands33%vs0%

Multi-Subject100%vs50%

Truthfulness74%vs41%

openai/gpt-image-2fal/bytedance/seedream-v4

Photorealism100%vs67%

Physics & Reflections58%vs42%

World Knowledge83%vs33%

Professional Studio100%vs74%

openai/gpt-image-2fal/bytedance/seedream-v4

Camera & Lighting100%vs83%

Color Precision100%vs75%

Photorealism100%vs33%

Graphical design100%vs79%

openai/gpt-image-2fal/bytedance/seedream-v4

Layout & Design100%vs78%

Data Visualisation100%vs33%

Style Diversity100%vs92%