Visual Reasoning on DeepTumorVQA
69.6Adjacent Organ ScorePhoton
Evaluation results
| Method | Links | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| PhotonEvaluation Mode=Multi-choice, Model Parameters=3B2026.03 | 69.6 | 54.9 | 37 | 53.9 | 77.6 | 35.6 | 70.3 | 86.5 | 98.5 | 53.5 | 47.5 | 66 | 79.1 | 82.9 | 65.3 | — | — | |
| M3D-P3Evaluation Mode=Multi-choice, Model Parameters=4B2026.03 | 60.9 | 57.6 | 36.4 | 53.9 | 78.3 | 31 | 68.4 | 86 | 78.4 | 54.9 | 47.5 | 66.7 | 73.6 | 83.9 | 62.7 | — | — | |
| CT-CHATEvaluation Mode=Multi-choice, Model Parameters=7B2026.03 | 60.9 | 57.2 | 37.2 | 54.4 | 78.1 | 34 | 67.2 | 86.2 | 79.6 | 45.1 | 46.3 | 65.5 | 73.6 | 82.1 | 62 | — | — | |
| RadFMEvaluation Mode=Multi-choice, Model Parameters=13B2026.03 | 60.9 | 59.1 | 38.6 | 55.5 | 76.6 | 34 | 66.4 | 86.1 | 79 | 49.3 | 46.9 | 66.1 | 74.6 | 82.1 | 62.5 | — | — | |
| M3D-L2Evaluation Mode=Multi-choice, Model Parameters=7B2026.03 | 56.5 | 56.7 | 37 | 54.1 | 77.8 | 31 | 67.2 | 86.1 | 78.1 | 50.7 | 43.8 | 66 | 73.6 | 83.6 | 61.6 | — | — | |
| RadFMEvaluation Mode=Free-text, Model Parameters=13B2026.03 | 43.5 | 45.6 | 38.6 | 52.1 | 23.2 | 33.4 | 67.2 | 50.6 | 0.1 | 52.1 | 51.3 | 62.1 | 75.9 | 18.9 | 43.9 | — | — | |
| RandEvaluation Mode=Multi-choice2026.03 | 33.3 | 33.3 | 33.3 | 33.3 | 25 | 39.2 | 25 | 25 | 32.8 | 50 | 33.3 | 25 | 50 | 30.5 | 33.5 | — | — | |
| M3D-P3Evaluation Mode=Free-text, Model Parameters=4B2026.03 | 30.4 | 59.2 | 35.6 | 54.8 | 23.3 | 33.7 | 51 | 53.4 | 0 | 53.5 | 46.9 | 58.6 | 73.6 | 13.9 | 42 | — | — | |
| CT-CHATEvaluation Mode=Free-text, Model Parameters=7B2026.03 | 30.4 | 58.9 | 37 | 54.2 | 26.9 | 35.3 | 51.3 | 53.4 | 0 | 57.7 | 43.1 | 57.4 | 73.6 | 19.7 | 42.8 | — | — | |
| PhotonEvaluation Mode=Free-text, Model Parameters=3B2026.03 | 30.4 | 35.9 | 39.6 | 57.1 | 31 | 35 | 72.3 | 54.6 | 91.7 | 63.4 | 45.6 | 79.8 | 84.5 | 20.7 | 53 | — | — | |
| MerlinEvaluation Mode=Multi-choice, Model Parameters=7B2026.03 | 21.7 | 47 | 34.7 | 31.7 | 26.3 | 30.7 | 24.1 | 58.3 | 45.5 | 52.1 | 33.1 | 25.7 | 73.6 | 29.6 | 38.2 | — | — | |
| MerlinEvaluation Mode=Free-text, Model Parameters=7B2026.03 | 17.4 | 57.7 | 35 | 52.6 | 18.2 | 35.9 | 52.4 | 53.4 | 0 | 45.1 | 38.8 | 57.7 | 73.6 | 11.3 | 39.2 | — | — | |
| M3D-L2Evaluation Mode=Free-text, Model Parameters=7B2026.03 | 17.4 | 56.1 | 37 | 54.4 | 20.9 | 35.3 | 53.3 | 53.4 | 0 | 53.5 | 46.9 | 56.9 | 73.6 | 12.2 | 40.8 | — | — |