| image-captioning-on-nocaps-in-domain | PaLI | #1 | CIDEr: 149.1 |
| image-captioning-on-nocaps-in-domain | PaLI | #4 | CIDEr: 121.09B1: 88.02B2: 75.21B3: 59.38B4: 41.16… |
| image-captioning-on-nocaps-near-domain | PaLI | #2 | CIDEr: 124.35B1: 88.57B2: 75.56B3: 58.99B4: 39.98… |
| image-captioning-on-nocaps-near-domain | PaLI | #8 | SPICE: 15.75 |
| image-captioning-on-nocaps-out-of-domain | PaLI | #1 | CIDEr: 126.67B1: 86.28B2: 71.19B3: 52.63B4: 32.0… |
| image-classification-on-imagenet-v2 | ViT-e | #2 | Top 1 Accuracy: 84.3 |
| image-classification-on-objectnet | ViT-e | #11 | Top-1 Accuracy: 72.0 |
| visual-question-answering-on-ok-vqa | PaLI 17B | #3 | Accuracy: 64.5 |
| visual-question-answering-on-textvqa-test-1 | PaLI | #1 | overall: 73.1 |
| visual-question-answering-on-vizwiz-2020-vqa | PaLI | #1 | overall: 73.3 |
| visual-question-answering-on-vqa-v2-test-dev | PaLI | #1 | Accuracy: 84.3 |
| zero-shot-transfer-image-classification-on-1 | LiT ViT-e | #4 | Accuracy (Private): 85.4 |
| zero-shot-transfer-image-classification-on-1 | PaLI | #15 | Accuracy (Private): 72.11 |
| zero-shot-transfer-image-classification-on-3 | LiT ViT-e | #3 | Accuracy (Private): 80.6 |
| zero-shot-transfer-image-classification-on-3 | PaLI | #11 | Accuracy (Private): 64.46 |
| zero-shot-transfer-image-classification-on-4 | LiT ViT-e | #2 | Accuracy: 96.1 |
| zero-shot-transfer-image-classification-on-4 | PaLI | #10 | Accuracy: 81.97 |
| zero-shot-transfer-image-classification-on-5 | LiT ViT-e | #3 | Accuracy (Private): 88.0 |
| zero-shot-transfer-image-classification-on-5 | PaLI | #11 | Accuracy (Private): 44.7 |
| zero-shot-transfer-image-classification-on-6 | LiT ViT-e | #2 | Accuracy (Private): 84.9 |
| zero-shot-transfer-image-classification-on-6 | PaLI | #9 | Accuracy (Private): 42.62Top 5 Accuracy: 58.35 |