Medical Reasoning Grounding on U-MRG-14K (test)
32.42IoU (General)MedReasoner-7B
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MedReasoner-7BModel Category=Grounding-Specific MLLM, ASM=MedSAM22025.08 | 32.42 | 26.55 | 37.78 | 3,027 | 3,281 | 51.5 | 3,472 | 11.66 | 50.75 | 29.91 | 33.58 | 37.19 | 30.48 | |
| Qwen2.5-VL-72BModel Category=General MLLM, ASM=MedSAM22025.08 | 18.32 | 12.39 | 29.71 | 1,360 | 2,006 | 38.3 | 1,551 | 8.74 | 35.25 | 20.64 | 20.69 | 30.19 | 16.92 | |
| SegZero-7BModel Category=Grounding-Specific MLLM, ASM=MedSAM22025.08 | 16.14 | 5.23 | 26.05 | 1,166 | 2,337 | 40.23 | 1,312 | 9.35 | 22.18 | 20.68 | 12.58 | 29.46 | 21.93 | |
| VLMR1-REC-3BModel Category=Grounding-Specific MLLM, ASM=MedSAM22025.08 | 13.96 | — | 22.19 | 864 | 2,181 | 25.09 | 819 | 10.69 | 29.77 | 21.35 | 8.76 | 26.59 | 21.41 | |
| Qwen2.5VL-7BModel Category=General MLLM, ASM=MedSAM22025.08 | 12.61 | 7.14 | 22.73 | 684 | 2,397 | 29.35 | 837 | 9.22 | 20.79 | 20.46 | 8 | 24.97 | 19.4 | |
| HuatuoGPT-7BModel Category=Medical-Specific MLLM, ASM=MedSAM22025.08 | 10.13 | 5.23 | 19.76 | 588 | 1,816 | 3.88 | 663 | 9.56 | 22.94 | 15.58 | 8.25 | 16.12 | 15.87 | |
| Lingshu-7BModel Category=Medical-Specific MLLM, ASM=MedSAM22025.08 | 8.19 | 3.73 | 16.48 | 403 | 1,572 | 6.97 | 627 | 8.06 | 19.77 | 8.63 | 6.34 | 13.31 | 11.99 | |
| MedR1-2BModel Category=Medical-Specific MLLM, ASM=MedSAM22025.08 | 8.18 | 3.6 | 14.73 | 353 | 1,255 | 1.1 | 353 | 8.14 | 25.58 | 8.81 | 4.39 | 13.57 | 17.35 | |
| SAM4MLLM-8BModel Category=Grounding-Specific MLLM, ASM=MedSAM22025.08 | 7.94 | — | 16.49 | 630 | 1,469 | 5.09 | 581 | 7.46 | 12.61 | 11.99 | 6.24 | 11.96 | 12.4 | |
| Gemini-2.5-flashModel Category=General MLLM, ASM=MedSAM22025.08 | 7.86 | 3.24 | 14.29 | 399 | 569 | 6.39 | 777 | 6.63 | 16.37 | 9.08 | 7.15 | 13.91 | 11.4 | |
| Chiron-o1-8BModel Category=Medical-Specific MLLM, ASM=MedSAM22025.08 | 6.4 | 2.46 | 10.05 | 382 | 690 | 4.29 | 420 | 5.99 | 12.86 | 9.5 | 5.53 | 11.31 | 10.86 | |
| InternVL3-8BModel Category=General MLLM, ASM=MedSAM22025.08 | 5.7 | 2.46 | 9.23 | 372 | 654 | 2.02 | 367 | 5.56 | 14.44 | 7.88 | 3.78 | 8.71 | 9 | |
| MedGamma-4BModel Category=Medical-Specific MLLM, ASM=MedSAM22025.08 | 5.39 | 1.9 | 8.9 | 423 | 692 | 1.28 | 341 | 4.78 | 17.22 | 6.92 | 3.17 | 3.9 | 10.04 | |
| InternVL3-78BModel Category=General MLLM, ASM=MedSAM22025.08 | 4.02 | 1.55 | 7.23 | 204 | 295 | 2.33 | 212 | 6.12 | 12.21 | 4.19 | 1.33 | 8.19 | 5.62 | |
| MiniInternVL-4BModel Category=Medical-Specific MLLM, ASM=MedSAM22025.08 | 2.88 | 0.85 | 4.76 | 188 | 267 | 0.68 | 160 | 3.45 | 7.99 | 3.59 | 1.56 | 3.76 | 6.59 | |
| GPT-4oModel Category=General MLLM, ASM=MedSAM22025.08 | 2.65 | 1.12 | 4.72 | 92 | 91 | 3.29 | 36 | 2.8 | 11.7 | 1.83 | 1.01 | 4.16 | 6.37 |