Backward Tracing on OVO-Bench Reactive QA 1.0 (test)
56.57EPM
ROMA
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.01 | 56.57 | 46.62 | 20.97 | |
2026.01 | 56.57 | 46.27 | 22.58 | |
2026.01 | 55.89 | 47.3 | 23.66 | |
2026.01 | 55.22 | 45.95 | 27.96 | |
2026.01 | 54.88 | 46.62 | 20.97 | |
2026.01 | 53.87 | 47.97 | 29.03 | |
2026.01 | 48.48 | 55.41 | 4.3 | |
2026.01 | 39.06 | 37.16 | 5.91 | |
2026.01 | 22.22 | 18.8 | 12.18 | |
2026.01 | 10.44 | 8.78 | 0.54 |