Language-to-Execution Grounding on LabGuard-Bench stress benchmark (Source-held-out)
76.5Tag F1
LabGuard-Hybrid
Updated 25d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.06 | 76.5 | 20.4 | - | 58.2 | 84.1 | 68.7 | |
2026.06 | 75.7 | 20.6 | - | 56.8 | 83.4 | 67.5 | |
2026.06 | 45.1 | 33.3 | - | 47.1 | 77.8 | 58.7 |