Paper Reproduction on RE-Bench Weighted
93.2Success RateBaseline
Evaluation results
| Method | Links | |
|---|---|---|
| BaselineReproduced Paper=bam, Artifact Type=Baseline2026.04 | 93.2 | |
| ARAReproduced Paper=pinn, Artifact Type=ARA2026.04 | 92.2 | |
| ARAReproduced Paper=bam, Artifact Type=ARA2026.04 | 88.2 | |
| ARAReproduced Paper=stochastic-interpolants, Artifact Type=ARA2026.04 | 86.7 | |
| BaselineReproduced Paper=stochastic-interpolants, Artifact Type=Baseline2026.04 | 85.3 | |
| ARAReproduced Paper=mechanistic-und., Artifact Type=ARA2026.04 | 76.2 | |
| ARAReproduced Paper=all-in-one, Artifact Type=ARA2026.04 | 72.8 | |
| BaselineReproduced Paper=rice, Artifact Type=Baseline2026.04 | 71.8 | |
| BaselineReproduced Paper=pinn, Artifact Type=Baseline2026.04 | 71 | |
| ARAReproduced Paper=rice, Artifact Type=ARA2026.04 | 69.9 | |
| BaselineReproduced Paper=adaptive-pruning, Artifact Type=Baseline2026.04 | 65.8 | |
| ARAReproduced Paper=sequential-neural, Artifact Type=ARA2026.04 | 64.8 | |
| ARAReproduced Paper=Mean, Artifact Type=ARA2026.04 | 64.4 | |
| ARAReproduced Paper=adaptive-pruning, Artifact Type=ARA2026.04 | 63.5 | |
| BaselineReproduced Paper=all-in-one, Artifact Type=Baseline2026.04 | 60.4 | |
| BaselineReproduced Paper=Mean, Artifact Type=Baseline2026.04 | 57.4 | |
| ARAReproduced Paper=self-composing-pol., Artifact Type=ARA2026.04 | 57.3 | |
| BaselineReproduced Paper=mechanistic-und., Artifact Type=Baseline2026.04 | 55 | |
| ARAReproduced Paper=fre, Artifact Type=ARA2026.04 | 53.2 | |
| ARAReproduced Paper=bbox, Artifact Type=ARA2026.04 | 49.8 | |
| BaselineReproduced Paper=sequential-neural, Artifact Type=Baseline2026.04 | 49.3 | |
| BaselineReproduced Paper=self-expansion, Artifact Type=Baseline2026.04 | 48.9 | |
| BaselineReproduced Paper=self-composing-pol., Artifact Type=Baseline2026.04 | 47.8 | |
| ARAReproduced Paper=sample-specific-masks, Artifact Type=ARA2026.04 | 42.7 | |
| BaselineReproduced Paper=sample-specific-masks, Artifact Type=Baseline2026.04 | 42.3 | |
| BaselineReproduced Paper=bbox, Artifact Type=Baseline2026.04 | 40.8 | |
| BaselineReproduced Paper=ftrl, Artifact Type=Baseline2026.04 | 38.8 | |
| ARAReproduced Paper=self-expansion, Artifact Type=ARA2026.04 | 38.2 | |
| ARAReproduced Paper=test-time-model-adapt., Artifact Type=ARA2026.04 | 35.1 | |
| BaselineReproduced Paper=test-time-model-adapt., Artifact Type=Baseline2026.04 | 35 | |
| BaselineReproduced Paper=fre, Artifact Type=Baseline2026.04 | 34.4 | |
| ARAReproduced Paper=ftrl, Artifact Type=ARA2026.04 | 33 |