Semantic Recognition on AIDE 5->5 rollout (test)
73.35DBR (F1)
Non-causal (bidir)
Updated 27d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 73.35 | 74.46 | 88.65 | 68.82 | |
2026.05 | 73.22 | 73.97 | 90.54 | 62.09 | |
2026.05 | 68.07 | 72.61 | 90.15 | 68.34 | |
2026.05 | 62.52 | 68.75 | 87.94 | 69.09 | |
2026.05 | 56.7 | 52.71 | - | - | |
2026.05 | 54.04 | 60.07 | 26.39 | 14 | |
2026.05 | 53.82 | 50.68 | - | - | |
2026.05 | 45.87 | 49.1 | 87.85 | 65.97 | |
2026.05 | 37.26 | 41.69 | - | - | |
2026.05 | 24.56 | 24.35 | 26.39 | 14 | |
2026.05 | 18.96 | 22.66 | - | - | |
2026.05 | 8.27 | 14.94 | - | - |