Our new X account is live! Follow @wizwand_team for updates

Natural Language Understanding on GLUE (test) (SST2, QNLI, RTE Subset)

92.31QNLI Score

Baseline

Updated 4d ago

Evaluation Results

Method	Links
Baseline 2025.10		92.31	76.41	93.16	87.29
D-Det RGN 2025.10		91.9	70.28	93.58	85.25
D-Full Random 2025.10		91.54	73.77	93.27	86.19
TRaDy 2025.10		91.36	73.53	93.31	86.07
D-Full Random 2025.10		91.23	65.1	93.85	83.39
D-Det RGN 2025.10		91.23	75.09	93.04	86.45
TRaDy 2025.10		91.23	68.83	93.43	84.5
D-Det RGN 2025.10		90.97	76.29	92.51	86.59
Baseline 2025.10		90.81	62.45	91.74	81.67
D-Det RGN 2025.10		90.78	77.02	93	86.93
D-Det RGN 2025.10		90.47	60.17	91.67	80.77
TRaDy 2025.10		90.05	59.57	93.31	80.98
D-Full Random 2025.10		89.99	58.12	93.12	80.41
D-Det RGN 2025.10		89.83	60.53	91.48	80.61
TRaDy 2025.10		89.71	57.16	93.31	80.06
D-Full Random 2025.10		89.69	57.4	93.23	80.11
D-Det RGN 2025.10		89	60.05	91.25	80.1
TRaDy 2025.10		88.97	57.16	90.86	79
D-Full Random 2025.10		88.68	58.24	89.6	78.84
D-Det RGN 2025.10		87.78	57.28	91.17	78.74
D-Full Random 2025.10		85.85	54.99	89.76	76.87
TRaDy 2025.10		85.84	56.68	90.1	77.54
TRaDy 2025.10		84.56	57.88	89.6	77.35
D-Full Random 2025.10		84.5	56.32	89.41	76.74
D-Full Random 2025.10		84.5	58.24	89.41	77.38
TRaDy 2025.10		84.38	57.76	89.53	77.22