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 ImageBench V1 run.

replicate/google/imagen-4-fast

API

Imagen 4 Fast is the speed- and cost-optimized tier of Google DeepMind's Imagen 4 family, tuned for low-latency, high-volume generation. It trades some fidelity for faster turnaround while retaining Imagen 4's prompt adherence and improved text rendering.

Maker: Google DeepMind
Family: Imagen 4
Model Size: not disclosed
unknown
Cost: $0.02 / image
high
Run Target: replicate/google/imagen-4-fast
Effective Request: aspect_ratio: 1:1 · seed: 7
Sources: Imagen 4 Fast — Replicate Announcing Imagen 4 Fast — Google Developers Blog