Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Runtime monitor execution on LabUtopia L1-L4 chemistry-held-out grounding 1.0 (hydrochloric acid)
Loading...
14.3
Unsafe Events
LabGuard-Hybrid
13.164
20.832
28.5
36.168
Jun 30, 2026
Unsafe Events
False Interventions
Task Success Rate
Updated 25d ago
Evaluation Results
Method
Method
Links
Unsafe Events
False Interventions
Task Success Rate
LabGuard-Hybrid
2026.06
14.3
4.6
0.893
Base Grounder + Constraint decoding
Backbone=Qwen3-8B, Dec...
2026.06
16.2
5.1
0.879
Base Grounder + LoRA fine-tuning
Backbone=Qwen3-8B, Fin...
2026.06
18.6
5.7
0.864
Qwen2.5-72B
Evaluation Protocol=0-...
2026.06
31.5
8.4
0.742
Base Grounder
Backbone=Qwen3-8B
2026.06
36.9
10.5
0.708
Regex BL
2026.06
42.7
9.8
0.653
Feedback
Search any
task
Search any
task