Medical Visual Question Answering on Medical VQA
96.76Accuracy (CT)Evo-PI
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Evo-PIBase Model=Med-R1 [12], RLVR Algorithm=GRPO2026.06 | 96.76 | 93.19 | 91.95 | 87.2 | 94.62 | 98.9 | 99.82 | 91.01 | 94.12 | |
| Evo-PIBase Model=Med-R1 [12], RLVR Algorithm=GSPO2026.06 | 96.28 | 93.34 | 90.81 | 87.39 | 92.98 | 99.34 | 99.82 | 90.38 | 93.91 | |
| Evo-PIBase Model=HuatuoGPT-Vision [11], RLVR Algorithm=GSPO2026.06 | 87.97 | 90.21 | 93.69 | 95.8 | 91.38 | 98.24 | 91.09 | 93.67 | 92.95 | |
| Evo-PIBase Model=HuatuoGPT-Vision [11], RLVR Algorithm=GRPO2026.06 | 87.97 | 90.21 | 93.69 | 95.8 | 94.18 | 98.24 | 91.09 | 93.67 | 92.95 | |
| Med-R1Base Model=Qwen 2-VL-2B, Modality-specific submodels=true2026.06 | 71.6 | 83.38 | 90.19 | 74.47 | 51.44 | 89.46 | 77.73 | 78.54 | 77.1 | |
| Qwen 2.5-VL-3BBase Model=Qwen 2.5-VL-3B2026.06 | 71.03 | 60.78 | 69.81 | 59.86 | 53.64 | 68.39 | 44.09 | 74.62 | 62.78 | |
| Qwen 2-VL-7BBase Model=Qwen 2-VL-7B2026.06 | 68.18 | 57.19 | 74.44 | 62.5 | 54.52 | 63.23 | 38.27 | 71.97 | 61.29 | |
| Qwen 2-VL-72BBase Model=Qwen 2-VL-72B2026.06 | 67.97 | 65.31 | 72.58 | 67.84 | 69.39 | 72.76 | 51.39 | 72.11 | 68.05 | |
| Qwen 2.5-VL-7BBase Model=Qwen 2.5-VL-7B2026.06 | 67.36 | 70.06 | 70.56 | 60.04 | 55.33 | 55.7 | 33.55 | 75.63 | 61.03 | |
| Qwen 2.5-VL-72BBase Model=Qwen 2.5-VL-72B2026.06 | 66.18 | 69.75 | 71.04 | 69.37 | 63.64 | 69.22 | 69.85 | 79.81 | 67.71 | |
| HuatuoGPT-VisionBase Model=Qwen 2.5-VL-7B2026.06 | 65.34 | 68.41 | 76.3 | 71.3 | 68.66 | 77.63 | 48.18 | 80.05 | 69.48 | |
| MedVInT2026.06 | 40.74 | 29.11 | 31.84 | 32.02 | 43.1 | 23.26 | 41.26 | 55.1 | 37.05 | |
| Qwen 2-VL-2BBase Model=Qwen 2-VL-2B2026.06 | 40.23 | 41.77 | 46.85 | 42.08 | 44.1 | 38.28 | 38.64 | 48.23 | 42.52 | |
| Med-Flamingo2026.06 | 31.28 | 48.56 | 41.26 | 30.03 | 26.34 | 25.16 | 31.69 | 44.01 | 34.29 | |
| RadFM2026.06 | 27.56 | 39.21 | 36.86 | 27.97 | 24.06 | 32.8 | 16.57 | 30.95 | 29.5 | |
| LLaVA-Med2026.06 | 18.69 | 44.95 | 39.03 | 33.29 | 27.47 | 34.61 | 29.88 | 30.68 | 32.33 |