Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language-to-Execution Grounding on LabGuard-Bench stress benchmark (Random 80/20 split)
Loading...
100
Tag F1
Gold
67.032
75.591
84.15
92.709
Jun 30, 2026
Tag F1
Prediction Accuracy
Soft Score
Catch Rate
Precision
F1 Score
Updated 25d ago
Evaluation Results
Method
Method
Links
Tag F1
Prediction Accuracy
Soft Score
Catch Rate
Precision
F1 Score
Gold
Grounding Module=Gold
2026.06
100
100
-
77.1
93.1
84.4
LabGuard-Hybrid
Grounding Module=LabGu...
2026.06
93.8
87.5
-
58.6
85.4
69.5
LoRA (Qwen3-8B)
Grounding Module=LoRA,...
2026.06
93.4
87.2
-
58.6
85.4
69.5
Regex
Grounding Module=Regex
2026.06
68.3
54.2
-
48.6
79.1
60.2
Feedback
Search any
task
Search any
task