Preference Estimation on PE-FD=8 (test)
61.28Average Outcome Reward
AREW– AS + BT
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.03 | 61.28 | |
2026.03 | 55.61 | |
2026.03 | 55.21 | |
2026.03 | 47.89 | |
2026.03 | 39.62 | |
2026.03 | 30.52 | |
2026.03 | 8.42 | |
2026.03 | 3.14 | |
2026.03 | 2.67 |