| Benchmark | Model | Rank | Results |
|---|---|---|---|
| image-captioning-on-flickr30k-captions-test | FewVLM | #4 | CIDEr: 31.0SPICE: 10.0 |
| visual-question-answering-on-gqa-test-dev | FewVLM (zero-shot) | #15 | Accuracy: 29.3 |
| visual-question-answering-on-ok-vqa | FewVLM | #30 | Accuracy: 16.5 |
| visual-question-answering-on-vqa-v2-val | Few VLM (zero-shot) | #8 | Accuracy: 47.7 |