Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Failure Taxonomy Recovery on RoboFail expert taxonomy
Loading...
92
CP
Unsupervised Failure Taxonomy Discovery Framework
77.96
81.605
85.25
88.895
Jun 6, 2025
CP
TC
SAS
Updated 1mo ago
Evaluation Results
Method
Method
Links
CP
TC
SAS
Unsupervised Failure Taxonomy Discovery Framework
Mode=Aggregation
2025.06
92
100
95.8
BERTopic-LLM
2025.06
87.5
87.5
87.5
Unsupervised Failure Taxonomy Discovery Framework
Mode=Single Run
2025.06
81.8
90
84.9
BERTopic
2025.06
78.5
62.5
69.6
Feedback
Search any
task
Search any
task