Visual Question Answering on SB VQA
70.5Balanced AccuracySlideChat
Evaluation results
| Method | Links | |
|---|---|---|
| SlideChatMode=WSI2025.11 | 70.5 | |
| GIANT GPT-5 x5Mode=WSI2025.11 | 58.5 | |
| GIANT GPT-5Mode=WSI2025.11 | 58 | |
| Patho-R1-7BMode=Thumb2025.11 | 57.5 | |
| Patho-R1-7BMode=Patch2025.11 | 56.5 | |
| GPT-5Mode=Thumb2025.11 | 54 | |
| Qwen3-VL-235BMode=Thumb2025.11 | 52.5 | |
| Pathgen-LLaVAMode=Patch2025.11 | 52 | |
| GPT-5Mode=Patch2025.11 | 51.5 | |
| Pathgen-LLaVAMode=Thumb2025.11 | 50.5 | |
| GIANT Qwen3Mode=WSI2025.11 | 50 | |
| PathAgentMode=WSI2025.11 | 49.5 | |
| Qwen3-VL-235BMode=Patch2025.11 | 48.5 | |
| GIANT GPT-4oMode=WSI2025.11 | 46.5 | |
| TITANMode=WSI2025.11 | 39 | |
| Quilt-LLaVAMode=Patch2025.11 | 37 | |
| Quilt-LLaVAMode=Thumb2025.11 | 33.5 | |
| MedGemma 1.5Mode=WSI2025.11 | 31.7 | |
| GPT-4oMode=Patch2025.11 | 23 | |
| GPT-4oMode=Thumb2025.11 | 12 |