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

TensorTrust

Benchmarks

Task NameDataset NameSOTA ResultTrend
Overrefusal evaluationTensorTrust overrefusal
Performance Score91
2
Instruction Hierarchy RobustnessTensorTrust user (dev)
Score91
2
Instruction Hierarchy RobustnessTensorTrust sys-user
Score94
2
Showing 3 of 3 rows