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

SQuAD, HellaSwag, and HeadQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
LLM Query RoutingSQuAD, HellaSwag, and HeadQA (out-of-domain)
Accuracy89
11
Showing 1 of 1 rows