Measurement on DeepTumorVQA
83.3Lesion Volume ScoreCT-CHAT
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| CT-CHATEvaluation Mode=Multi-choice, Model Parameters=7B2026.03 | 83.3 | 63.7 | 75 | 74 | — | — | |
| M3D-P3Evaluation Mode=Multi-choice, Model Parameters=4B2026.03 | 82.5 | 64 | 75.4 | 74 | — | — | |
| PhotonEvaluation Mode=Multi-choice, Model Parameters=3B2026.03 | 82.5 | 64.2 | 75.6 | 74.1 | — | — | |
| M3D-L2Evaluation Mode=Multi-choice, Model Parameters=7B2026.03 | 81.5 | 63.8 | 74.7 | 73.3 | — | — | |
| RadFMEvaluation Mode=Multi-choice, Model Parameters=13B2026.03 | 81.5 | 64.7 | 75.5 | 73.9 | — | — | |
| PhotonEvaluation Mode=Free-text, Model Parameters=3B2026.03 | 26.5 | 77.7 | 71.7 | 58.7 | — | — | |
| MerlinEvaluation Mode=Multi-choice, Model Parameters=7B2026.03 | 25.3 | 25.4 | 26.2 | 25.6 | — | — | |
| RandEvaluation Mode=Multi-choice2026.03 | 25 | 25 | 25 | 25 | — | — | |
| RadFMEvaluation Mode=Free-text, Model Parameters=13B2026.03 | 11.2 | 60.8 | 58.3 | 43.4 | — | — | |
| M3D-L2Evaluation Mode=Free-text, Model Parameters=7B2026.03 | 8.5 | 49 | 53.5 | 37 | — | — | |
| MerlinEvaluation Mode=Free-text, Model Parameters=7B2026.03 | 7.9 | 48.7 | 52.6 | 36.4 | — | — | |
| M3D-P3Evaluation Mode=Free-text, Model Parameters=4B2026.03 | 7.9 | 49.1 | 52.8 | 36.6 | — | — | |
| CT-CHATEvaluation Mode=Free-text, Model Parameters=7B2026.03 | 7.5 | 51.3 | 54.9 | 37.9 | — | — |