Object-level reasoning on UNOBench Hard synthetic (test)
67.6OP
Gemini Robotics-ER 1.5
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.11 | 67.6 | 24.3 | 33 | |
2025.11 | 63 | 43.6 | 48.7 | |
2025.11 | 46.1 | 14.4 | 20.8 | |
2025.11 | 44.6 | 20.1 | 25.7 | |
2025.11 | 13.9 | 10.8 | 10.6 | |
2025.11 | 7.8 | 2 | 3.1 | |
2025.11 | 6.1 | 1.7 | 2.6 | |
2025.11 | 3.7 | 2.2 | 2.7 |