CausalGym
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
CausalGym filler_gap_hierarchy
100Completeness
16
CausalGym cleft
100Completeness
16
CausalGym agr_sv_num_obj-relc
100Completeness
16
CausalGym
100Completeness
8
CausalGym
97.64Completeness
8
CausalGym
100Completeness
8
CausalGym
100Completeness
8
CausalGym
100Completeness
8
CausalGym
100Completeness
8
CausalGym
100Completeness
8
CausalGym npi_any_subj-relc
100Completeness
8
CausalGym agr_gender
100Completeness
8