Referring Expression Grounding on RefCOCO (testB)
89.5AccuracyMM1.5-30B
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MM1.5-30BModel Size Category=Larger (>13B)2024.09 | 89.5 | — | — | |
| Ferret-V2-13BModel Size Category=Larger (>13B)2024.09 | 88.9 | — | — | |
| Ferret-V2-7BModel Size Category=7B2024.09 | 88.7 | — | — | |
| G-DINO2025.05 | 88.2 | — | — | |
| MM1.5-7BModel Size Category=7B2024.09 | 86.7 | — | — | |
| MM1.5-3B-MoEModel Size Category=3B, Architecture=MoE2024.09 | 86.4 | — | — | |
| MM1.5-3BModel Size Category=3B2024.09 | 86.1 | — | — | |
| Argus-X3-8B2025.05 | 85.4 | — | — | |
| MiniGPT-7B2025.05 | 85.3 | — | — | |
| QwenVL-7B2025.05 | 85.3 | — | — | |
| MM1.5-1B-MoEModel Size Category=1B, Architecture=MoE2024.09 | 84.8 | — | — | |
| Qwen-VL-7BModel Size Category=7B2024.09 | 84.5 | — | — | |
| Ferret-13BModel Size Category=Larger (>13B)2024.09 | 84.4 | — | — | |
| MiniGPT-v2-7BModel Size Category=7B2024.09 | 84.3 | — | — | |
| Ferret-7BModel Size Category=7B2024.09 | 82.5 | — | — | |
| Ferret-7B2025.05 | 82.5 | — | — | |
| MM1.5-1BModel Size Category=1B2024.09 | 81.9 | — | — | |
| MDETR2025.05 | 81.4 | — | — | |
| InternVL2-8B2025.05 | 80.7 | — | — | |
| UniTAB2025.05 | 80.6 | — | — | |
| Shikra-7B2025.05 | 80.2 | — | — | |
| TransVG2025.05 | 78.3 | — | — | |
| SPHINX-TinyModel Size Category=1B2024.09 | 77.9 | — | — | |
| OFA-L2025.05 | 76.4 | — | — | |
| InternVL2Model Size Category=3B2024.09 | 75.9 | — | — | |
| VILLA2025.05 | 74.8 | — | — | |
| UNITER2025.05 | 74.2 | — | — | |
| MCNProposal-free=true, Visual Extractor=VGG-162021.03 | 73.09 | 65.69 | — | |
| MAttNet2025.05 | 69.3 | — | — | |
| MAttNetProposal-free=false, Visual Extractor=ResNet-1012021.03 | 69.28 | 68.33 | — | |
| Iterative ShrinkingProposal-free=true, Visual Extractor=ResNet-1012021.03 | 68.1 | 68.63 | — | |
| FAOAVGProposal-free=true, Visual Extractor=DarkNet-532021.03 | 67.59 | 61.79 | — | |
| RCCFProposal-free=true, Visual Extractor=DLA-342021.03 | 66.73 | 67.3 | — | |
| DGAProposal-free=false, Visual Extractor=VGG-162021.03 | 65.53 | 65.26 | — | |
| SLRProposal-free=false, Visual Extractor=ResNet-1012021.03 | 64.96 | 61.25 | — | |
| LLaVA-OneVision-7BModel Size Category=7B2024.09 | 61.6 | — | — | |
| Phi-3-Vision-4BModel Size Category=3B2024.09 | 36.1 | — | — | |
| MM1-1BModel Size Category=1B2024.09 | 0 | — | — | |
| MM1-3BModel Size Category=3B2024.09 | 0 | — | — | |
| MM1-7BModel Size Category=7B2024.09 | 0 | — | — | |
| MM1-30BModel Size Category=Larger (>13B)2024.09 | 0 | — | — | |
| Qwen2.5-VL-3BBackbone=Qwen2.5-VL-3B2026.06 | — | — | 83 | |
| SequentialBackbone=Qwen2.5-VL-3B2026.06 | — | — | 84.2 | |
| Visual Para-Thinker (3B)Backbone=Qwen2.5-VL-3B2026.06 | — | — | 87.7 | |
| Visual Para-Thinker++ (3B)Backbone=Qwen2.5-VL-3B2026.06 | — | — | 90.4 |