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

148-query

Benchmarks

Task NameDataset NameSOTA ResultTrend
Stylized Dialogue148-query style-3 persona (test)
Context4.696
3
Stylized Dialogue148-query style-2 persona (test)
Context4.169
3
Stylized Dialogue148-query style-0 persona (test)
Context Score4.622
3
Stylized Dialogue148-query Average across 9 styles (test)
Context Relevance4.463
3
Stylized Dialogue Generation148-query (test)
CS-SB1 Score0.904
3
Showing 5 of 5 rows