Metric: accuracy (higher is better)
| # | Model↕ | accuracy▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | LXMERT | 70.1 | No | Visual Spatial Reasoning | 2022-04-30 | Code |
| 2 | ViLT | 69.3 | No | Visual Spatial Reasoning | 2022-04-30 | Code |
| 3 | CLIP (finetuned) | 65.1 | No | Visual Spatial Reasoning | 2022-04-30 | Code |
| 4 | CLIP (frozen) | 56 | No | Visual Spatial Reasoning | 2022-04-30 | Code |
| 5 | VisualBERT | 55.2 | No | Visual Spatial Reasoning | 2022-04-30 | Code |