| Benchmark | Model | Rank | Results |
|---|---|---|---|
| visual-question-answering-on-vizwiz-2020-vqa | Unified-IO XL | #3 | overall: 57.4 |
| image-captioning-on-nocaps-val-overall | Unified-IO XL | #11 | CIDEr: 100.0 |
| visual-question-answering-on-ok-vqa | Unified-IO XL | #15 | Accuracy: 54.0 |
| image-classification-on-imagenet | Unified-IO XL | #818 | Top 1 Accuracy: 79.1% |
| object-categorization-on-grit | Unified-IOXL | – | Categorization (ablation): 61.7Categorization (test): 60.8 |
| object-localization-on-grit | Unified-IOXL | – | Localization (ablation): 67.0Localization (test): 67.1 |