Judge Performance Evaluation on SynJudge
0.54TCC (RMSE)
QwenVL_trained
Updated 1mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2025.06 | 0.54 | 0.72 | 0.68 | 0.67 | 95.4 | |
2025.06 | 0.55 | 0.7 | 0.72 | 0.72 | 94.5 | |
2025.06 | 0.81 | 1.09 | 0.96 | 1.2 | 87.5 | |
2025.06 | 0.96 | 0.9 | 1.06 | 1.03 | 86.6 | |
2025.06 | 1.01 | 1.02 | 0.98 | 1.18 | 86.5 |