Open-ended scientific discovery on 40-task evaluation set Overall 2025
4.78Expert Score (ES)OpenEvolve
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| OpenEvolve2026.06 | 4.78 | 1.44 | 351 | 16 | 4.6 | |
| Raw agent2026.06 | 4.22 | 2.47 | 381 | 47 | 12.3 | |
| SAGA2026.06 | 3.8 | 2.66 | 250 | 52 | 20.8 | |
| StatefulDiscovery2026.06 | 3.76 | 3.09 | 261 | 64 | 24.5 | |
| AutoDiscovery2026.06 | 3.7 | 2.59 | 387 | 36 | 9.3 |