Visual Question Answering on PANDA
27Balanced AccuracyTITAN
Evaluation Results
| Method | Links | |
|---|---|---|
| TITANMode=WSI2025.11 | 27 | |
| GIANT GPT-5 x5Mode=WSI2025.11 | 25.6 | |
| GIANT GPT-5Mode=WSI2025.11 | 23.4 | |
| GPT-5Mode=Patch2025.11 | 21.1 | |
| MedGemma 1.5Mode=WSI2025.11 | 19.6 | |
| Patho-R1-7BMode=Thumb2025.11 | 19.5 | |
| PathAgentMode=WSI2025.11 | 19.2 | |
| Pathgen-LLaVAMode=Thumb2025.11 | 19.1 | |
| Qwen3-VL-235BMode=Thumb2025.11 | 18.7 | |
| Pathgen-LLaVAMode=Patch2025.11 | 17.4 | |
| SlideChatMode=WSI2025.11 | 17 | |
| Patho-R1-7BMode=Patch2025.11 | 17 | |
| Quilt-LLaVAMode=Patch2025.11 | 16.7 | |
| GIANT Qwen3Mode=WSI2025.11 | 15.5 | |
| Qwen3-VL-235BMode=Patch2025.11 | 15.2 | |
| GIANT GPT-4oMode=WSI2025.11 | 14.8 | |
| GPT-5Mode=Thumb2025.11 | 12.4 | |
| Quilt-LLaVAMode=Thumb2025.11 | 8.8 | |
| GPT-4oMode=Patch2025.11 | 0 | |
| GPT-4oMode=Thumb2025.11 | 0 |