Open-ended Scientific Discovery on BLADE open-ended discovery (evaluation set)
4.8Expert ScoreOpenEvolve
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| OpenEvolve2026.06 | 4.8 | 1.44 | 91 | 3 | 3.3 | |
| AutoDiscovery2026.06 | 4.42 | 2.63 | 130 | 11 | 8.5 | |
| Raw agent2026.06 | 4.11 | 2.33 | 115 | 11 | 9.6 | |
| StatefulDiscovery2026.06 | 3.95 | 2.86 | 86 | 22 | 25.6 | |
| SAGA2026.06 | 3.48 | 2.37 | 96 | 11 | 11.5 |