Visual Question Answering on Expert VQA
62.5Balanced AccuracyGIANT GPT-5 x5
Evaluation results
| Method | Links | |
|---|---|---|
| GIANT GPT-5 x5Mode=WSI2025.11 | 62.5 | |
| GIANT GPT-5Mode=WSI2025.11 | 57 | |
| GIANT Qwen3Mode=WSI2025.11 | 53.9 | |
| GPT-5Mode=Thumb2025.11 | 50 | |
| Patho-R1-7BMode=Thumb2025.11 | 48.4 | |
| Qwen3-VL-235BMode=Thumb2025.11 | 48.4 | |
| PathAgentMode=WSI2025.11 | 44.5 | |
| Patho-R1-7BMode=Patch2025.11 | 43.8 | |
| TITANMode=WSI2025.11 | 43.8 | |
| Pathgen-LLaVAMode=Patch2025.11 | 42.2 | |
| Qwen3-VL-235BMode=Patch2025.11 | 42.2 | |
| GPT-5Mode=Patch2025.11 | 41.4 | |
| GIANT GPT-4oMode=WSI2025.11 | 40.6 | |
| Pathgen-LLaVAMode=Thumb2025.11 | 38.3 | |
| SlideChatMode=WSI2025.11 | 37.5 | |
| MedGemma 1.5Mode=WSI2025.11 | 35.9 | |
| Quilt-LLaVAMode=Thumb2025.11 | 35.9 | |
| Quilt-LLaVAMode=Patch2025.11 | 31.2 | |
| GPT-4oMode=Patch2025.11 | 22.7 | |
| GPT-4oMode=Thumb2025.11 | 7 |