Paper Reproduction on RE-Bench Easy tier
100Success RateBaseline
Evaluation Results
| Method | Links | |
|---|---|---|
| BaselineReproduced Paper=bam, Artifact Type=Baseline2026.04 | 100 | |
| BaselineReproduced Paper=bbox, Artifact Type=Baseline2026.04 | 97.8 | |
| ARAReproduced Paper=stochastic-interpolants, Artifact Type=ARA2026.04 | 97.7 | |
| ARAReproduced Paper=bam, Artifact Type=ARA2026.04 | 97.1 | |
| ARAReproduced Paper=pinn, Artifact Type=ARA2026.04 | 96.2 | |
| ARAReproduced Paper=sample-specific-masks, Artifact Type=ARA2026.04 | 95.6 | |
| BaselineReproduced Paper=sample-specific-masks, Artifact Type=Baseline2026.04 | 95.6 | |
| BaselineReproduced Paper=stochastic-interpolants, Artifact Type=Baseline2026.04 | 95.5 | |
| ARAReproduced Paper=sequential-neural, Artifact Type=ARA2026.04 | 95.2 | |
| BaselineReproduced Paper=test-time-model-adapt., Artifact Type=Baseline2026.04 | 94.4 | |
| ARAReproduced Paper=bbox, Artifact Type=ARA2026.04 | 93.3 | |
| BaselineReproduced Paper=self-composing-pol., Artifact Type=Baseline2026.04 | 93.3 | |
| BaselineReproduced Paper=all-in-one, Artifact Type=Baseline2026.04 | 91.3 | |
| ARAReproduced Paper=adaptive-pruning, Artifact Type=ARA2026.04 | 90.9 | |
| ARAReproduced Paper=all-in-one, Artifact Type=ARA2026.04 | 90.4 | |
| BaselineReproduced Paper=adaptive-pruning, Artifact Type=Baseline2026.04 | 89.8 | |
| ARAReproduced Paper=test-time-model-adapt., Artifact Type=ARA2026.04 | 87.8 | |
| ARAReproduced Paper=self-composing-pol., Artifact Type=ARA2026.04 | 87.5 | |
| ARAReproduced Paper=mechanistic-und., Artifact Type=ARA2026.04 | 85.7 | |
| ARAReproduced Paper=Mean, Artifact Type=ARA2026.04 | 85.1 | |
| BaselineReproduced Paper=mechanistic-und., Artifact Type=Baseline2026.04 | 82.5 | |
| BaselineReproduced Paper=Mean, Artifact Type=Baseline2026.04 | 80.2 | |
| ARAReproduced Paper=fre, Artifact Type=ARA2026.04 | 79.3 | |
| BaselineReproduced Paper=pinn, Artifact Type=Baseline2026.04 | 78.8 | |
| BaselineReproduced Paper=rice, Artifact Type=Baseline2026.04 | 74.1 | |
| ARAReproduced Paper=rice, Artifact Type=ARA2026.04 | 72.3 | |
| BaselineReproduced Paper=sequential-neural, Artifact Type=Baseline2026.04 | 69.3 | |
| BaselineReproduced Paper=fre, Artifact Type=Baseline2026.04 | 62.2 | |
| BaselineReproduced Paper=ftrl, Artifact Type=Baseline2026.04 | 36.2 | |
| ARAReproduced Paper=self-expansion, Artifact Type=ARA2026.04 | 34.7 | |
| ARAReproduced Paper=ftrl, Artifact Type=ARA2026.04 | 25 | |
| BaselineReproduced Paper=self-expansion, Artifact Type=Baseline2026.04 | 20.8 |