Rhetorical Role Labeling on SCOTUSCategory (test)
85.03Macro F1
Qwen-3-8B
Updated 2mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 85.03 | 86.38 | |
2026.05 | 84.57 | 86.57 | |
2026.05 | 83.88 | 85.89 | |
2026.05 | 83.83 | 86.13 | |
2026.05 | 83.73 | 85.91 | |
2026.05 | 83.15 | 85.7 | |
2026.05 | 82.85 | 84.95 | |
2026.05 | 82.83 | 85.76 | |
2026.05 | 82.54 | 85.13 | |
2026.05 | 82.19 | 85.12 | |
2026.05 | 82.13 | 84.99 | |
2026.05 | 81.81 | 84.21 | |
2026.05 | 81.7 | 84.46 | |
2026.05 | 81.59 | 84.25 |