Video Document Seeking on ViDoSeek
44.34Single ScoreLang2Act
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Lang2ActCategory=Tool-Enhanced VLMs2026.01 | 44.34 | 65.39 | 53.5 | |
| EVisRAGCategory=Multimodal Retrieval-Augmented Generation Models (MRAGs)2026.01 | 42.33 | 61.67 | 50.53 | |
| Pixel-ReasonerCategory=Tool-Enhanced VLMs2026.01 | 36.55 | 63.12 | 48.51 | |
| Vision-R1Category=Vision-Language Reasoning Models (VLRMs)2026.01 | 32.71 | 60.56 | 44.83 | |
| OpenVLThinkerCategory=Vision-Language Reasoning Models (VLRMs)2026.01 | 29.77 | 61.97 | 43.78 | |
| ThinkLite-VLCategory=Vision-Language Reasoning Models (VLRMs)2026.01 | 26.36 | 61.77 | 41.77 | |
| MM-Search-R1Category=Multimodal Retrieval-Augmented Generation Models (MRAGs)2026.01 | 25.12 | 61.37 | 40.89 | |
| VRAG-RLCategory=Tool-Enhanced VLMs2026.01 | 24.81 | 61.57 | 40.81 | |
| GOTCategory=Prompting Methods2026.01 | 24.5 | 55.13 | 37.83 | |
| VisionMattersCategory=Vision-Language Reasoning Models (VLRMs)2026.01 | 24.34 | 61.37 | 40.46 | |
| DirectCategory=Prompting Methods2026.01 | 22.64 | 55.33 | 36.87 | |
| TOTCategory=Prompting Methods2026.01 | 21.24 | 59.15 | 37.74 | |
| VisDomCategory=Multimodal Retrieval-Augmented Generation Models (MRAGs)2026.01 | 18.76 | 57.14 | 35.46 | |
| R1-OnevisionCategory=Vision-Language Reasoning Models (VLRMs)2026.01 | 16.43 | 57.95 | 34.5 |