Visual Question Answering on DocHaystack 200
79.82AccuracyQwen2-VL-f.t. + V-RAG
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2-VL-f.t. + V-RAGFramework=V-RAG, Resolution=Low-resolution, Adaptation=LoRA2024.11 | 79.82 | |
| Qwen2-VL + V-RAGFramework=V-RAG, Resolution=Low-resolution2024.11 | 74.31 | |
| GPT-4o + V-RAGFramework=V-RAG, Resolution=Low-resolution2024.11 | 72.48 | |
| LLaVA-OV + V-RAGFramework=V-RAG2024.11 | 65.14 | |
| Gemini + V-RAGFramework=V-RAG2024.11 | 65.14 | |
| Gemini2024.11 | 48.62 | |
| GPT-4oResolution=Low-resolution2024.11 | 23.85 | |
| Qwen2-VLResolution=Low-resolution2024.11 | 12.84 | |
| MIRAGE2024.11 | 3.67 |