Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Laboratory-language grounding on LabGuard-Bench chemistry-held-out hydrochloric acid 1.0
Loading...
91.8
Tag F1
LabGuard-Hybrid
51.24
61.77
72.3
82.83
Jun 30, 2026
Tag F1
Pred Soft Score
Pred EM Score
Updated 25d ago
Evaluation Results
Method
Method
Links
Tag F1
Pred Soft Score
Pred EM Score
LabGuard-Hybrid
2026.06
91.8
74.3
57.2
Base Grounder + Constraint decoding
Backbone=Qwen3-8B, Dec...
2026.06
90.2
71.5
54.8
Base Grounder + LoRA fine-tuning
Backbone=Qwen3-8B, Fin...
2026.06
88.7
68.4
52.3
Qwen2.5-72B
Evaluation Protocol=0-...
2026.06
73.6
40.3
38.7
Base Grounder
Backbone=Qwen3-8B
2026.06
68.4
32.8
28.3
Regex BL
2026.06
52.8
35.2
18.5
Feedback
Search any
task
Search any
task