Treatment Response Prediction on Treatment Response (held-out set)
58F1 (weighted)MOOZY
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MOOZYEvaluation Protocol=Frozen model evaluated with MLP probe2026.03 | 58 | 0.68 | 48 | |
| MOOZYEvaluation Protocol=Frozen-feature MLP probe2026.03 | 58 | 0.68 | 48 | |
| PRISMEvaluation Protocol=Frozen-feature MLP probe2026.03 | 57 | 0.69 | 51 | |
| CONCH v1.5Evaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 53 | 0.67 | 47 | |
| CHIEFEvaluation Protocol=Frozen-feature MLP probe2026.03 | 53 | 0.7 | 48 | |
| MUSKEvaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 52 | 0.68 | 47 | |
| BackboneEvaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 51 | 0.66 | 46 | |
| Giga PathEvaluation Protocol=Frozen-feature MLP probe2026.03 | 51 | 0.68 | 40 | |
| Phikon v2Evaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 49 | 0.65 | 38 | |
| MadeleineEvaluation Protocol=Frozen-feature MLP probe2026.03 | 49 | 0.59 | 35 | |
| TITANEvaluation Protocol=Frozen-feature MLP probe2026.03 | 49 | 0.6 | 37 | |
| UNI v2Evaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 45 | 0.62 | 37 |