End-to-end Question Answering on TechSlides
70.9Overall ScoreSlideAgent
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SlideAgentMethod Type=Multimodal RAG (Type 2) and Agentic Methods (Type 3), Base Model=GPT-4o2025.10 | 70.9 | 82.5 | 66.2 | |
| ViDoRAGMethod Type=Multimodal RAG (Type 2) and Agentic Methods (Type 3), Base Model=GPT-4o2025.10 | 68.7 | 78.2 | 59.4 | |
| Qwen2.5-VL-32B-InstructType=12025.10 | 67.5 | 87.5 | 60.6 | |
| VDocRAGMethod Type=Multimodal RAG (Type 2) and Agentic Methods (Type 3), Base Model=GPT-4o2025.10 | 67 | 80.5 | 57 | |
| VisRAGMethod Type=Multimodal RAG (Type 2) and Agentic Methods (Type 3), Base Model=GPT-4o2025.10 | 64.7 | 72.6 | 54.7 | |
| COLPALIMethod Type=Multimodal RAG (Type 2) and Agentic Methods (Type 3), Base Model=GPT-4o2025.10 | 64.1 | 73.2 | 54.5 | |
| GPT-4oMethod Type=Multimodal LLMs (Type 1)2025.10 | 63.4 | 78.3 | 53.9 | |
| SlideAgentType=3, Base Model=InternVL3-8B2025.10 | 63.1 | 78 | 61.7 | |
| ViDoRAGType=2, Base Model=InternVL3-8B2025.10 | 61.4 | 61.9 | 59.3 | |
| Claude-4.1-OpusMethod Type=Multimodal LLMs (Type 1)2025.10 | 61 | 81.4 | 52.3 | |
| Phi-3-vision-128k-instructType=12025.10 | 59.4 | 60 | 59.1 | |
| Qwen2.5-VL-7B-InstructType=12025.10 | 59.3 | 52.5 | 65.9 | |
| VDocRAGType=2, Base Model=InternVL3-8B2025.10 | 59.2 | 60.7 | 58.3 | |
| COLPALIType=2, Base Model=InternVL3-8B2025.10 | 57.1 | 60.9 | 55.2 | |
| VisRAGType=2, Base Model=InternVL3-8B2025.10 | 56.8 | 57.7 | 55.4 | |
| InternVL3-8BType=12025.10 | 55.4 | 57.5 | 54.4 | |
| Claude-3.5-HaikuMethod Type=Multimodal LLMs (Type 1)2025.10 | 52.5 | 80.2 | 39.5 | |
| Gemini-2.5-FlashMethod Type=Multimodal LLMs (Type 1)2025.10 | 51.1 | 71.4 | 41.2 | |
| Gemini-2.0-FlashMethod Type=Multimodal LLMs (Type 1)2025.10 | 50.4 | 67.6 | 41.6 | |
| Gemini-2.5-Flash-LiteMethod Type=Multimodal LLMs (Type 1)2025.10 | 47.3 | 58.1 | 41.9 | |
| llava-v1.6-vicuna-13b-hfType=12025.10 | 45.2 | 40 | 49.1 | |
| Llama-3.2-11B-Vision-InstructType=12025.10 | 41.4 | 52.5 | 36.2 | |
| llava-v1.6-mistral-7b-hfType=12025.10 | 34.4 | 37.5 | 32.2 | |
| llava-1.5-13b-hfType=12025.10 | 28.1 | 17.5 | 45 | |
| llava-1.5-7b-hfType=12025.10 | 23.3 | 12.5 | 38.7 |