Visual Question Answering on InfoHaystack-200
67.74AccuracyQwen2-VL-f.t. + V-RAG
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2-VL-f.t. + V-RAGFramework=V-RAG, Resolution=Low-resolution, Adaptation=LoRA2024.11 | 67.74 | |
| Qwen2-VL + V-RAGFramework=V-RAG, Resolution=Low-resolution2024.11 | 65.81 | |
| GPT-4o + V-RAGFramework=V-RAG, Resolution=Low-resolution2024.11 | 63.23 | |
| Gemini + V-RAGFramework=V-RAG2024.11 | 57.42 | |
| LLaVA-OV + V-RAGFramework=V-RAG2024.11 | 41.94 | |
| Gemini2024.11 | 21.94 | |
| GPT-4oResolution=Low-resolution2024.11 | 20 | |
| Qwen2-VLResolution=Low-resolution2024.11 | 14.19 | |
| MIRAGE2024.11 | 7.1 |