Path-level reasoning on UNOBench synthetic Hard (test)
56.8SR-P
UNOGrasp
Updated 4d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2025.11 | 56.8 | 55.3 | 54.5 | 0.51 | |
2025.11 | 42.2 | 35.4 | 37.2 | 0.67 | |
2025.11 | 38.1 | 33.3 | 34.3 | - | |
2025.11 | 33.9 | 31.5 | 31.9 | - | |
2025.11 | 17.2 | 13.4 | 14.6 | 0.89 | |
2025.11 | 14.9 | 14.8 | 13.8 | 0.68 | |
2025.11 | 11.7 | 9.4 | 10.1 | 0.91 | |
2025.11 | 9.7 | 17.2 | 10.2 | 0.79 | |
2025.11 | 9.7 | 9.4 | 8.9 | 0.89 | |
2025.11 | 5.9 | 5.7 | 5.4 | 0.74 |