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/leonardoai/lucid-origin

API

Lucid Origin is Leonardo.Ai's flagship general-purpose text-to-image model, built for strong prompt adherence and sharp Full-HD in-image text, around ELO ~1121 on the image arena. Benchmarked in its default 'standard' generation mode. Adds a new maker (Leonardo.Ai) to the board.

Maker: Leonardo.Ai
Family: Lucid Origin
Model Size: not disclosed
unknown
Cost: $0.0167 / image
high
Run Target: replicate/leonardoai/lucid-origin
Effective Request: aspect_ratio: 1:1 · generation_mode: standard
Sources: Lucid Origin on Replicate Leonardo Lucid Origin