Visual Question Answering (VQA) on ImageNet
Metric: Follow-up ClipMatch@5 (higher is better)
LeaderboardDataset
Loading chart...
Results
Submit a result| # | Model↕ | Follow-up ClipMatch@5▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | BLIP-2 OPT | 83.54 | No | Open-ended VQA benchmarking of Vision-Language m... | 2024-02-11 | Code |
- 83.54Follow-up ClipMatch@5· 2024-02-11