KRAS Mutation Prediction on KRAS mutation (held-out set)
85Weighted F1MOOZY
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MOOZYEvaluation Protocol=Frozen model evaluated with MLP probe2026.03 | 85 | 80 | 79 | |
| CONCH v1.5Evaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 80 | 74 | 77 | |
| BackboneEvaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 78 | 74 | 76 | |
| MUSKEvaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 76 | 70 | 72 | |
| UNI v2Evaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 74 | 71 | 69 | |
| Phikon v2Evaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 74 | 68 | 68 | |
| MOOZYEvaluation Protocol=Frozen-feature MLP probe2026.03 | 0.85 | 0.8 | 0.79 | |
| MadeleineEvaluation Protocol=Frozen-feature MLP probe2026.03 | 0.81 | 0.7 | 0.77 | |
| TITANEvaluation Protocol=Frozen-feature MLP probe2026.03 | 0.8 | 0.8 | 0.81 | |
| CHIEFEvaluation Protocol=Frozen-feature MLP probe2026.03 | 0.77 | 0.76 | 0.74 | |
| Giga PathEvaluation Protocol=Frozen-feature MLP probe2026.03 | 0.77 | 0.72 | 0.76 | |
| PRISMEvaluation Protocol=Frozen-feature MLP probe2026.03 | 0.72 | 0.61 | 0.63 |