LabGuard-Bench
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
LabGuard-Bench 1.0 (source-held-out)
79.4Tag F1
10
LabGuard-Bench (random 80/20 split)
91.5Type Accuracy
9
LabGuard-Bench chemistry-held-out hydrochloric acid 1.0
91.8Tag F1
6
LabGuard-Bench stress benchmark (Random 80/20 split)
100Tag F1
4
LabGuard-Bench stress benchmark (Source-held-out)
76.5Tag F1
3