GPT-Image 1.5 leads on human preference — 1256 vs 1145 Elo (#6 of 158 in the Image Arena). The right pick still depends on style, speed and licensing — details below.
GPT-Image 1.5✓fal-ai/gpt-image-1.5vs
Imagineart 1.5 Previewimagineart/imagineart-1.5-preview/text-to-image| Human-preference Elo | 1256 | 1145 |
| Arena rank | #6 of 158 | #49 of 158 |
| Category | text-to-image | text-to-image |
| License | commercial | commercial |
By human preference, GPT-Image 1.5 currently rates higher (1256 vs 1145 Elo). Preference votes measure typical output quality; test both on your own prompts for style fit.
Both are text to image models available as hosted API endpoints — GPT-Image 1.5 (fal-ai/gpt-image-1.5) and Imagineart 1.5 Preview (imagineart/imagineart-1.5-preview/text-to-image).
See the full best text-to-image models ranking.