Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

FTRACE-TREx

Benchmarks

Task NameDataset NameSOTA ResultTrend
Model Behavior TracingFTRACE-TREx (20K Candidate Set)
MRR0.1927
3
Model Behavior TracingFTRACE-TREx (15K Candidate Set)
MRR0.2101
3
Showing 2 of 2 rows