Visual Question Answering on MedXpertQA Pathology 90 samples
25.56AccuracyPathGen-LLaVA-13B
Evaluation Results
| Method | Links | |
|---|---|---|
| PathGen-LLaVA-13BModel Size=Large, Thinking Ability=Without2025.05 | 25.56 | |
| LLaVA-Med-v1.5-Mistral-7BModel Size=Large, Thinking Ability=Without2025.05 | 24.44 | |
| Patho-R1-3BModel Size=Small, Thinking Ability=With2025.05 | 24.44 | |
| Qwen2.5VL-3BModel Size=Small, Thinking Ability=With2025.05 | 23.33 | |
| InternVL2.5-8BModel Size=Large, Thinking Ability=With2025.05 | 22.22 | |
| Patho-R1-7BModel Size=Large, Thinking Ability=With2025.05 | 22 | |
| Llama-3.2V-11B-cotModel Size=Large, Thinking Ability=With2025.05 | 21.11 | |
| DeepSeek-VL2-TinyModel Size=Small, Thinking Ability=With2025.05 | 17.78 | |
| LLaVA-Onevision-7BModel Size=Large, Thinking Ability=With2025.05 | 16.67 | |
| InternVL3-8BModel Size=Large, Thinking Ability=With2025.05 | 15.56 | |
| Llama-3.2-11B-Vision-InstructModel Size=Large, Thinking Ability=With2025.05 | 13.33 | |
| VILA1.5-3BModel Size=Small, Thinking Ability=Without2025.05 | 12.22 | |
| Llama3.2-3B-vlModel Size=Small, Thinking Ability=Without2025.05 | 12.22 | |
| HuatuoGPT-Vision-7BModel Size=Large, Thinking Ability=Without2025.05 | 12.22 | |
| Qwen2.5VL-7BModel Size=Large, Thinking Ability=With2025.05 | 12.22 | |
| InternVL2-8BModel Size=Large, Thinking Ability=With2025.05 | 10 | |
| Quilt-LLaVA-v1.5-7BModel Size=Large, Thinking Ability=Without2025.05 | 7.78 | |
| Paligemma2-3b-pt-224Model Size=Small, Thinking Ability=Without2025.05 | 0 |