Reward Model Transfer on Anthropic Helpful (AH)
9.95AOG
SEAM
Updated 8d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 9.95 | - | - | -5.72 | |
2026.05 | 8.2 | - | - | -3.39 | |
2026.05 | 8.19 | - | - | 8.19 | |
2026.05 | 8.06 | - | - | 5.94 | |
2026.05 | 5.88 | - | - | 3.5 | |
2026.05 | 4.41 | - | - | 4.41 | |
2026.05 | 3.26 | - | - | 3.08 | |
2026.05 | 3.13 | - | - | 3.13 | |
2026.05 | 1.46 | - | - | 1.46 | |
2026.05 | 1.37 | - | - | 0.96 | |
2026.05 | 0.6 | - | - | 0.6 | |
2026.05 | 0.25 | - | - | 0.25 | |
2026.05 | 0.17 | - | - | -6.48 | |
2026.05 | -0.04 | - | - | -3.1 | |
2026.05 | -1.58 | - | - | -3.88 | |
2026.05 | -2.61 | - | - | -2.61 | |
2026.05 | - | 98.7 | 3.13 | - | |
2026.05 | - | 70.3 | 2.23 | - | |
2026.05 | - | -411.4 | -13.04 | - | |
2026.05 | - | 106.9 | 3.39 | - | |
2026.05 | - | 173.1 | 0.45 | - | |
2026.05 | - | 661.5 | 1.72 | - | |
2026.05 | - | -1.3 | -3.42 | - | |
2026.05 | - | 1 | 2.75 | - |