Robot Failure Detection on BridgeData Fail V2
85Execution Accuracy
Guardian-8B-Thinking
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.12 | 85 | 91 | |
2025.12 | 75 | 86 | |
2025.12 | 72 | 86 | |
2025.12 | 66 | 71 | |
2025.12 | 58 | 54 | |
2025.12 | 57 | - | |
2025.12 | 53 | 61 |
Guardian-8B-Thinking
| Method | Links | ||
|---|---|---|---|
2025.12 | 85 | 91 | |
2025.12 | 75 | 86 | |
2025.12 | 72 | 86 | |
2025.12 | 66 | 71 | |
2025.12 | 58 | 54 | |
2025.12 | 57 | - | |
2025.12 | 53 | 61 |