Multi-step Reasoning on MuSR
57.36Murder Mystery Score
n=64 (RL)
Updated 22d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.05 | 57.36 | 45.98 | 38.57 | |
2026.05 | 56.94 | 47.08 | 39.07 | |
2026.05 | 53.15 | 46.23 | 23.46 | |
2026.05 | 50.5 | 45.25 | 25.7 |
n=64 (RL)
| Method | Links | |||
|---|---|---|---|---|
2026.05 | 57.36 | 45.98 | 38.57 | |
2026.05 | 56.94 | 47.08 | 39.07 | |
2026.05 | 53.15 | 46.23 | 23.46 | |
2026.05 | 50.5 | 45.25 | 25.7 |