Grammaticality Judgment
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
96.7Anaphora
28
Feb 26, 2026
76.4BLiMP Grammaticality Score
6
May 19, 2026
82.3BLiMP Accuracy (Epoch 2)
5
Jul 1, 2026
81BLiMP Grammaticality Judgment (Epoch 1)
5
Jul 1, 2026