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

CLIMAQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question AnsweringClimaQA
Accuracy82.53
54
Climate Question AnsweringCLIMAQA (held-out)
DBS46.3
9
Question AnsweringClimaQA Freeform
BertScore81.3
7
Showing 3 of 3 rows