Multi-modal Question Answering on PathVQA
65.9AccuracyLingshu-32B
Evaluation Results
| Method | Links | |
|---|---|---|
| Lingshu-32BModel Category=Open-source, Model Scale=~32B2026.01 | 65.9 | |
| PulseMind-72BModel Category=Open-source, Model Scale=~72B2026.01 | 64.9 | |
| PulseMind-32BModel Category=Open-source, Model Scale=~32B2026.01 | 62 | |
| o1Model Category=Proprietary2026.01 | 57.3 | |
| GPT-4oModel Category=Proprietary2026.01 | 55.5 | |
| Gemini2.5-proModel Category=Proprietary2026.01 | 55.4 | |
| InternVL3-78BModel Category=Open-source, Model Scale=~72B2026.01 | 51 | |
| InternVL3-38BModel Category=Open-source, Model Scale=~32B2026.01 | 51 | |
| LLAVA-med-34BModel Category=Open-source, Model Scale=~32B2026.01 | 48.8 | |
| HuatuoGPT-vision-34BModel Category=Open-source, Model Scale=~32B2026.01 | 44.4 | |
| Qwen2.5VL-72BModel Category=Open-source, Model Scale=~72B2026.01 | 42.3 | |
| Qwen2.5VL-32BModel Category=Open-source, Model Scale=~32B2026.01 | 41.9 |