Open World Video Understanding on WildVideo
63.2Average AccuracyG2F-RAG
Evaluation Results
| Method | Links | |
|---|---|---|
| G2F-RAGSize=14B, Base Model=InternVL3.52026.04 | 63.2 | |
| GPT-4o (2024-05-13)Size=-2026.04 | 62.1 | |
| G2F-RAGSize=8B, Base Model=InternVL3.52026.04 | 60.1 | |
| InternVL3.5Size=14B2026.04 | 60.1 | |
| G2F-RAGSize=7B, Base Model=LLaVA-Video2026.04 | 57 | |
| G2F-RAGSize=7B, Base Model=Qwen2.5-VL2026.04 | 55.4 | |
| Gemini1.5 ProSize=-2026.04 | 53.7 | |
| LLaVA-VideoSize=7B2026.04 | 53.4 | |
| InternVL3.5Size=8B2026.04 | 53 | |
| Qwen2.5-VLSize=7B2026.04 | 51.3 | |
| G2F-RAGSize=4B, Base Model=InternVL3.52026.04 | 47.1 | |
| MiniCPM-V 2.6Size=8B2026.04 | 46.4 | |
| InternVL3.5Size=4B2026.04 | 45.2 | |
| Qwen2.5-VLSize=3B2026.04 | 38.6 |