Long-horizon reasoning on EXPLORE-Bench Long
59.37Sobj Score
GLEN
Updated 23d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.07 | 59.37 | 2.67 | |
2026.07 | 59.17 | 2.7 | |
2026.07 | 58.06 | 2.61 | |
2026.07 | 58.02 | 2.63 | |
2026.07 | 56.83 | 2.71 | |
2026.07 | 47.62 | 2.41 |
GLEN
| Method | Links | ||
|---|---|---|---|
2026.07 | 59.37 | 2.67 | |
2026.07 | 59.17 | 2.7 | |
2026.07 | 58.06 | 2.61 | |
2026.07 | 58.02 | 2.63 | |
2026.07 | 56.83 | 2.71 | |
2026.07 | 47.62 | 2.41 |