| continual-learning-on-cifar100-20-tasks | kNN-CLIP | – | Average Accuracy: 90.8 |
| image-classification-on-cifar-10 | kNN-CLIP | – | Percentage correct: 97.3 |
| image-classification-on-cifar-100 | kNN-CLIP | – | Percentage correct: 81.7 |
| image-classification-on-imagenet | kNN-CLIP | – | Top 1 Accuracy: 79.8% |
| image-classification-on-imagenet-real | kNN-CLIP | – | Accuracy: 84% |
| image-classification-on-stl-10 | kNN-CLIP | – | Percentage correct: 99.6 |
| incremental-learning-on-imagenet-10-steps | kNN-CLIP | – | Average Incremental Accuracy: 85.5 |
| incremental-learning-on-imagenet100-10-steps | kNN-CLIP | – | Average Incremental Accuracy: 85.1 |