Histologic Grade Prediction on Histologic Grade (held-out set)
78F1 (weighted)MOOZY
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MOOZYEvaluation Protocol=Frozen model evaluated with MLP probe2026.03 | 78 | 75 | 77 | |
| MOOZYEvaluation Protocol=Frozen-feature MLP probe2026.03 | 78 | 75 | 77 | |
| Giga PathEvaluation Protocol=Frozen-feature MLP probe2026.03 | 77 | 77 | 77 | |
| CONCH v1.5Evaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 76 | 76 | 75 | |
| MUSKEvaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 75 | 74 | 75 | |
| MadeleineEvaluation Protocol=Frozen-feature MLP probe2026.03 | 75 | 74 | 74 | |
| BackboneEvaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 74 | 73 | 74 | |
| UNI v2Evaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 74 | 73 | 75 | |
| PRISMEvaluation Protocol=Frozen-feature MLP probe2026.03 | 73 | 67 | 73 | |
| TITANEvaluation Protocol=Frozen-feature MLP probe2026.03 | 73 | 71 | 73 | |
| Phikon v2Evaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 72 | 72 | 72 | |
| CHIEFEvaluation Protocol=Frozen-feature MLP probe2026.03 | 71 | 71 | 73 |