Category ranking · 7 models · checked 2026-10-13
Image generation
Ranked by GenEval, overall. Source: HiDream-I1 model card comparison table (vendor-reported).
GenEval, overall
3 with a published score, 4 not yet measured.
# | Model | Parameters | Score | Source | Licence |
|---|---|---|---|---|---|
| 1 | HiDream-I1 Full HiDream.ai | 17.1 B | 0.83Sourced | Source GenEval overall, model card table. | MIT |
| 2 | FLUX.1 [dev] Black Forest Labs | 11.9 B | 0.66Sourced | Source Third-party report: Flux.1-dev row in the HiDream-I1 model card. | FLUX.1 [dev] Non-Commercial Check terms before commercial use |
| 3 | Stable Diffusion XL Stability AI | 2.6 B | 0.55Sourced | Source Third-party report: SDXL row in the HiDream-I1 model card. | CreativeML OpenRAIL++-M |
| — | FLUX.1 [schnell] Black Forest Labs | 11.9 B | Not yet measured | — | Apache-2.0 |
| — | FLUX.1 Kontext [dev] Black Forest Labs | 11.9 B | Not yet measured | — | FLUX.1 [dev] Non-Commercial Check terms before commercial use |
| — | Qwen-Image Alibaba Qwen | 20.4 B | Not yet measured | Scores published as images only. | Apache-2.0 |
| — | Stable Diffusion 3.5 Medium Stability AI | 2.5 B | Not yet measured | — | Stability AI Community |
How to read this: one public benchmark per category, so you can compare like with like. We copy the published number and link it; we do not re-run it, average different benchmarks or fill gaps. Vendor-reported numbers use each vendor's own settings, so treat small gaps as ties. “Not yet measured” means we found no comparable public score, not that the model is weak.
Every model was checked against the Hugging Face API on 2026-10-13: it exists, is public, and has the parameter count and licence shown. Other categories: Math and reasoning · Coding · Vision-language · OCR and documents · Speech to text · Text to speech · Embeddings and rerankers · Small fast 'System 1' · Biomedical · Tool use and agents · Multilingual and translation · Time series · Robotics (VLA).
Machine-readable: /api/v1/categories/image-generation.json