Referring Expression Grounding on LVIS-Ref
87.7Accuracy (Box)Ferret-V2-13B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Ferret-V2-13BModel Size Category=Larger (>13B)2024.09 | 87.7 | 75.1 | |
| Ferret-V2-7BModel Size Category=7B2024.09 | 86.6 | 74.6 | |
| MM1.5-30BModel Size Category=Larger (>13B)2024.09 | 84.9 | 61.4 | |
| Ferret-13BModel Size Category=Larger (>13B)2024.09 | 80.5 | 68.4 | |
| Ferret-7BModel Size Category=7B2024.09 | 79.4 | 67.9 | |
| MM1.5-7BModel Size Category=7B2024.09 | 79.4 | 53.4 | |
| MM1.5-3B-MoEModel Size Category=3B, Architecture=MoE2024.09 | 79.3 | 54.5 | |
| MM1.5-3BModel Size Category=3B2024.09 | 76.3 | 59.5 | |
| MM1.5-1B-MoEModel Size Category=1B, Architecture=MoE2024.09 | 71.4 | 56.7 | |
| MM1.5-1BModel Size Category=1B2024.09 | 69.7 | 54.7 | |
| Phi-3-Vision-4BModel Size Category=3B2024.09 | 53.8 | 54.5 | |
| MM1-30BModel Size Category=Larger (>13B)2024.09 | 53.4 | 52.7 | |
| MM1-7BModel Size Category=7B2024.09 | 53.1 | 53.3 | |
| MM1-3BModel Size Category=3B2024.09 | 52.9 | 53.9 | |
| MM1-1BModel Size Category=1B2024.09 | 51.4 | 51.6 | |
| LLaVA-OneVision-7BModel Size Category=7B2024.09 | 51.2 | 51.4 | |
| InternVL2Model Size Category=3B2024.09 | 51 | 51.1 | |
| MiniCPM-v2-3BModel Size Category=3B2024.09 | 48.2 | 47.7 |