Image Classification on Oxford-IIIT Pet Dataset
88.5AccuracyGRIP
Evaluation Results
| Method | Links | |
|---|---|---|
| GRIPModel=Idefics2-8B2026.06 | 88.5 | |
| ViTModel=Idefics2-8B2026.06 | 88.1 | |
| DINOModel=Idefics2-8B2026.06 | 86.2 | |
| CLIPModel=Idefics2-8B2026.06 | 86.2 | |
| GRIPModel=Qwen2.5-VL-7B2026.06 | 83.9 | |
| ViTModel=Qwen2.5-VL-7B2026.06 | 79 | |
| CLIPModel=Qwen2.5-VL-7B2026.06 | 78.2 | |
| DINOModel=Qwen2.5-VL-7B2026.06 | 78.1 | |
| Zero ShotModel=Qwen2.5-VL-7B2026.06 | 75.9 | |
| Zero ShotModel=Idefics2-8B2026.06 | 55 |