Paper Reproduction on RE-Bench Hard tier
89.8Success RateARA
Evaluation Results
| Method | Links | |
|---|---|---|
| ARAReproduced Paper=pinn, Artifact Type=ARA2026.04 | 89.8 | |
| BaselineReproduced Paper=bam, Artifact Type=Baseline2026.04 | 89.5 | |
| ARAReproduced Paper=bam, Artifact Type=ARA2026.04 | 77.6 | |
| ARAReproduced Paper=stochastic-interpolants, Artifact Type=ARA2026.04 | 74.1 | |
| BaselineReproduced Paper=stochastic-interpolants, Artifact Type=Baseline2026.04 | 72.4 | |
| BaselineReproduced Paper=rice, Artifact Type=Baseline2026.04 | 68 | |
| ARAReproduced Paper=mechanistic-und., Artifact Type=ARA2026.04 | 67.1 | |
| BaselineReproduced Paper=pinn, Artifact Type=Baseline2026.04 | 65.9 | |
| ARAReproduced Paper=rice, Artifact Type=ARA2026.04 | 65.8 | |
| ARAReproduced Paper=all-in-one, Artifact Type=ARA2026.04 | 61.1 | |
| BaselineReproduced Paper=mechanistic-und., Artifact Type=Baseline2026.04 | 55 | |
| ARAReproduced Paper=Mean, Artifact Type=ARA2026.04 | 54.5 | |
| ARAReproduced Paper=self-composing-pol., Artifact Type=ARA2026.04 | 52.3 | |
| ARAReproduced Paper=sequential-neural, Artifact Type=ARA2026.04 | 51.6 | |
| ARAReproduced Paper=fre, Artifact Type=ARA2026.04 | 50.9 | |
| BaselineReproduced Paper=self-expansion, Artifact Type=Baseline2026.04 | 47.3 | |
| BaselineReproduced Paper=Mean, Artifact Type=Baseline2026.04 | 46 | |
| BaselineReproduced Paper=all-in-one, Artifact Type=Baseline2026.04 | 42 | |
| BaselineReproduced Paper=sequential-neural, Artifact Type=Baseline2026.04 | 39.7 | |
| ARAReproduced Paper=self-expansion, Artifact Type=ARA2026.04 | 39.3 | |
| BaselineReproduced Paper=self-composing-pol., Artifact Type=Baseline2026.04 | 37.2 | |
| BaselineReproduced Paper=adaptive-pruning, Artifact Type=Baseline2026.04 | 35 | |
| ARAReproduced Paper=ftrl, Artifact Type=ARA2026.04 | 32 | |
| ARAReproduced Paper=adaptive-pruning, Artifact Type=ARA2026.04 | 31.7 | |
| ARAReproduced Paper=bbox, Artifact Type=ARA2026.04 | 31.6 | |
| ARAReproduced Paper=sample-specific-masks, Artifact Type=ARA2026.04 | 31.1 | |
| BaselineReproduced Paper=ftrl, Artifact Type=Baseline2026.04 | 30 | |
| BaselineReproduced Paper=fre, Artifact Type=Baseline2026.04 | 28.6 | |
| BaselineReproduced Paper=sample-specific-masks, Artifact Type=Baseline2026.04 | 25.7 | |
| ARAReproduced Paper=test-time-model-adapt., Artifact Type=ARA2026.04 | 19.8 | |
| BaselineReproduced Paper=bbox, Artifact Type=Baseline2026.04 | 17.3 | |
| BaselineReproduced Paper=test-time-model-adapt., Artifact Type=Baseline2026.04 | 15.9 |