User Simulation on User Simulation Dataset Session-level (test)
95.21Role Score
UserLM-R1-32B
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.01 | 95.21 | 46.08 | 57.46 | 73.49 | |
2026.01 | 94.29 | 58.75 | 46.92 | 73.56 | |
2026.01 | 92.25 | 32.71 | 45.96 | 65.79 | |
2026.01 | 92 | 54.87 | 40.79 | 69.92 | |
2026.01 | 89.29 | 37.71 | 41.46 | 64.44 | |
2026.01 | 87.67 | 38.92 | 37.96 | 63.06 | |
2026.01 | 86.09 | 56.34 | 44.7 | 68.31 | |
2026.01 | 85.57 | 29.85 | 34.21 | 58.8 | |
2026.01 | 85.24 | 30.25 | 37.88 | 59.65 | |
2026.01 | 84.58 | 47.54 | 39.71 | 64.1 | |
2026.01 | 45.58 | 13.87 | 14.5 | 29.88 |