whatmodel.sh / image / Ovis-U1-3B
Ovis-U1-3B
↗ share
+ contribute
Ovis-U1-3B is an open-weights image model from Alibaba (AIDC-AI), released June 2025. Its published size is 3B parameters. Licence: apache-2.0.
Catalogue identity notes
Alibaba AIDC-AI's Ovis-U1 unified understanding/generation/editing model, 3B (AIDC-AI/Ovis-U1-3B, pinned cbc005d, Apache-2.0). WEAVE 'Ovis-U1 [67] 3B' and ViGoR 'Ovis-U1-3B (Wang et al., 2025a)' both name the single public release. Distinct from the catalogued ovis-image-7b. Comparison-only.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of Ovis-U1-3B, out of 197 with a score, then more from Alibaba (AIDC-AI).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 163 |  PixArt-α (PixArt-XL-2-1024-MS) | 36±2 | local | ||
| 164 |  Emu3 | 36±2 | local | ||
| 165 | Ovis-U1-3B | 35±6 | comparison only | ||
| 166 |  IF-XL | 35±2 | local | ||
| 167 |  Stable Diffusion XL 1.0 | 34±1 | api $0.0019/image +local | ||
| more from Alibaba (AIDC-AI) | |||||
| 113 | Ovis-Image-7B | 48±7 | local | ||
$ what it's good at
other tests2 not in a task · 86% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| WEAVEBench in-context multi-turn editing (Avg) | 42.2% ✎ | █▄▄·▄▄▄▄█·▄█ beats 1/12 | 68% |
| ViGoR-Bench zero-shot visual reasoning, image models (Result Avg) | 24.3% ✎ | ▂···▂·▂█▆▅·▂ beats 4/15 | 19% |
$ where to run it
No verified API or download recorded yet · add one
Weights and documentation: huggingface.co/AIDC-AI ↗
$ how the score was worked out · WEAVE: Unleashing and Benchma… 68%, ViGoR-Bench: How Far Are Visu… 19%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation (arXiv:2511.11434v1) | 1 | 68% |
| ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners? (arXiv:2603.25823v1) | 1 | 19% |
| prior · pull toward the middle | 14% | |
| weighted average | = 35.4 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json