whatmodel.sh / image / UniPic2-Metaquery-9B
UniPic2-Metaquery-9B
↗ share
+ contribute
UniPic2-Metaquery-9B is an open-weights image model from Skywork AI, released August 2025. Its published size is 9B parameters. Licence: mit.
Catalogue identity notes
Skywork UniPic 2.0 MetaQuery-style unified model, 9B (Skywork/UniPic2-Metaquery-9B, pinned 37a2f17, MIT). WEAVE 'UniPic2-Metaquery [73] 9B'; ViGoR 'UniPic2-M-9B (Wei et al., 2025)'. -GRPO and -Flash variants are separate repos and are not assumed. Comparison-only.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of UniPic2-Metaquery-9B, out of 197 with a score, then more from Skywork AI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 143 |  Midjourney V7 | 40±3 | comparison only | ||
| 144 |  UniWorld-V1 | 40±2 | comparison only | ||
| 145 | UniPic2-Metaquery-9B | 40±6 | comparison only | ||
| 146 |  Show-o2 1.5B-HQ | 40±3 | local | ||
| 147 | Skywork UniPic 1.5B | 40±6 | comparison only | ||
| more from Skywork AI | |||||
| 95 | UniPic 3 | 52±3 | comparison only | ||
| 128 | UniPic2-SD3.5M-Kontext-2B | 44±6 | comparison only | ||
$ what it's good at
other tests2 not in a task · 87% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| WEAVEBench in-context multi-turn editing (Avg) | 58.2% ✎ | █▄▄·▄▄▄▄█·▄█ beats 7/12 | 66% |
| ViGoR-Bench zero-shot visual reasoning, image models (Result Avg) | 8.0% ✎ | ▂···▃·▂█▆▅·▂ beats 1/15 | 21% |
$ where to run it
No verified API or download recorded yet · add one
Official weights and documentation: huggingface.co/Skywork ↗
$ how the score was worked out · WEAVE: Unleashing and Benchma… 66%, ViGoR-Bench: How Far Are Visu… 21%
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 | 66% |
| ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners? (arXiv:2603.25823v1) | 1 | 21% |
| prior · pull toward the middle | 13% | |
| weighted average | = 40.2 |
$ 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