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

CUS-QA

Benchmarks

Task NameDataset NameSOTA ResultTrend
NLG Meta-evaluationCUS-QA orig. (uk)
Kendall Correlation0.681
6
NLG Meta-evaluationCUS-QA orig. (sk)
Kendall Correlation0.788
6
NLG Meta-evaluationCUS-QA orig. (cs)
Kendall Correlation0.804
6
NLG Meta-evaluationCUS-QA en uk
Kendall Correlation0.577
6
NLG Meta-evaluationCUS-QA en (sk)
Kendall Correlation0.661
6
NLG Meta-evaluationCUS-QA en cs
Kendall Correlation0.73
6
Question Answering EvaluationCUS-QA orig.
CS95.6
6
Question Answering EvaluationCUS-QA en
CS Metric91.7
6
Showing 8 of 8 rows