Metric: Accuracy (higher is better)
| # | Model↕ | Accuracy▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | SMoLA-PaLI-X Specialist | 77.1 | Yes | Omni-SMoLA: Boosting Generalist Multimodal Model... | 2023-12-01 | - |
| 2 | PaLI-X-VPD | 76.6 | No | Visual Program Distillation: Distilling Tools an... | 2023-12-05 | - |
| 3 | SMoLA-PaLI-X Generalist (0 shot) | 70.7 | Yes | Omni-SMoLA: Boosting Generalist Multimodal Model... | 2023-12-01 | - |
| 4 | MoVie-ResNeXt | 56.8 | No | MoVie: Revisiting Modulated Convolutions for Vis... | 2020-04-24 | Code |
| 5 | RCN | 56.2 | No | TallyQA: Answering Complex Counting Questions | 2018-10-29 | Code |
| 6 | MoVie | 54.1 | No | MoVie: Revisiting Modulated Convolutions for Vis... | 2020-04-24 | Code |