Multi-modal Question Answering on VQA-RAD
87.1AccuracyPulseMind-72B
Evaluation results
| Method | Links | |
|---|---|---|
| PulseMind-72BModel Category=Open-source, Model Scale=~72B2026.01 | 87.1 | |
| PulseMind-32BModel Category=Open-source, Model Scale=~32B2026.01 | 83.2 | |
| Qwen2.5VL-72BModel Category=Open-source, Model Scale=~72B2026.01 | 80.3 | |
| Lingshu-32BModel Category=Open-source, Model Scale=~32B2026.01 | 76.5 | |
| Qwen2.5VL-32BModel Category=Open-source, Model Scale=~32B2026.01 | 73.8 | |
| InternVL3-78BModel Category=Open-source, Model Scale=~72B2026.01 | 73.6 | |
| GPT-4oModel Category=Proprietary2026.01 | 71.2 | |
| Gemini2.5-proModel Category=Proprietary2026.01 | 70.5 | |
| InternVL3-38BModel Category=Open-source, Model Scale=~32B2026.01 | 65.4 | |
| o1Model Category=Proprietary2026.01 | 63 | |
| HuatuoGPT-vision-34BModel Category=Open-source, Model Scale=~32B2026.01 | 61.4 | |
| LLAVA-med-34BModel Category=Open-source, Model Scale=~32B2026.01 | 58.6 |