Backward Tracing on OVOBench (test)
58.6EPM
Gemini-1.5-Pro
Updated 18d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.03 | 58.6 | 76.4 | 52.6 | 62.5 | |
| 57.6 | 54.1 | 49.5 | 54.4 | ||
2026.03 | 55.2 | 60.8 | 42.5 | 52.8 | |
2026.03 | 48.5 | 55.4 | 4.3 | 36.1 | |
2026.03 | 48.2 | 57.4 | 24.7 | 43.4 | |
2026.03 | 40.7 | 59.5 | 4.8 | 35 | |
2026.03 | 39.1 | 37.2 | 5.9 | 27.4 | |
2026.03 | 22.2 | 18.8 | 12.2 | 17.7 |