Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

LLM

Benchmarks

Task NameDataset NameSOTA ResultTrend
Binary Inconsistency DetectionLLM
Accuracy70.27
10
Robust SteganographyLLM Generative Text
Embedding Capacity (bits / 1k tokens)84.08
5
Span DetectionLLM
F1 Score0.3322
5
LanguageLLM-329M
Peak Performance (FP4/FP8)205
1
Showing 4 of 4 rows