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

LQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
ReasoningLQA
First-Token Accuracy40.6
24
Dialogue GenerationLQA (test)
BLEU-10.0927
8
Question AnsweringLQA
BLEU-144.1
8
Showing 3 of 3 rows