Response Similarity Evaluation on NUMINA
1.848C-Score
QwQ-32B-Preview
Updated 3mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2025.01 | 1.848 | 1.623 | 1.157 | 3.85 | |
2025.01 | 1.845 | 1.867 | 1.865 | 4.665 | |
2025.01 | 1.841 | 1.863 | 1.907 | 4.679 | |
2025.01 | 1.83 | 1.863 | 1.903 | 4.676 | |
2025.01 | 1.786 | 1.818 | 1.772 | 4.498 | |
2025.01 | 1.751 | 1.751 | 1.763 | 4.425 | |
2025.01 | 1.746 | 1.64 | 1.41 | 4.016 | |
| 1.662 | 1.524 | 1.185 | 3.757 | ||
2025.01 | 1.652 | 1.487 | 1.11 | 3.653 |