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

Pre-Ex-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Safety classificationPre-Ex-Bench
Accuracy94.01
20
Safety classificationPre-Ex-Bench (test)
Accuracy92.96
12
Showing 2 of 2 rows