| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Laboratory-language grounding | LabGuard-Bench 1.0 (source-held-out) | Tag F179.4 | 10 | |
| Laboratory-language grounding | LabGuard-Bench (random 80/20 split) | Type Accuracy91.5 | 9 | |
| Laboratory-language grounding | LabGuard-Bench chemistry-held-out hydrochloric acid 1.0 | Tag F191.8 | 6 | |
| Language-to-Execution Grounding | LabGuard-Bench stress benchmark (Random 80/20 split) | Tag F1100 | 4 | |
| Language-to-Execution Grounding | LabGuard-Bench stress benchmark (Source-held-out) | Tag F176.5 | 3 |