Trajectory Verification on SWE-bench OpenHands-LM-32B trajectories (Verified)
48.8RM@32
SWE-RM-30A3B
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.12 | 48.8 | 0.748 | 0.08 | |
2025.12 | 44.6 | 0.732 | 0.118 | |
2025.12 | 44.2 | - | - | |
2025.12 | 42.4 | - | - | |
2025.12 | 41.6 | 0.718 | 0.164 |