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

BrainRot

Benchmarks

Task NameDataset NameSOTA ResultTrend
Language ModelingBrainRot (Junk)
Perplexity79.97
6
Language ModelingBrainRot (Ctrl)
Perplexity (Ctrl)2.33
6
Data ValuationBrainRot
Purity87.6
5
Linear DatamodelingBrainRot (2K pool)
LDS0.204
5
Influence Function RetrievalBrainRot
Top-5 auPRC85.94
4
Showing 5 of 5 rows